© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44493
    Prev
    Next
    INDEX
    Explanations

    <link

    np_max-act · gemini-2.0-flash

    The neuron is looking for HTML markup tokens—especially tags and attributes in the document head such as `<`, `head`, `link`, `meta`, `stylesheet`, and related CSS/HTML boilerplate.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gaps
    -0.06
    包含
    -0.06
    速
    -0.06
    pagina
    -0.06
     frosting
    -0.06
     Grill
    -0.06
    然
    -0.06
    appropri
    -0.06
    frames
    -0.06
    ระบ
    -0.06
    POSITIVE LOGITS
    (predictions
    0.07
     dayan
    0.06
    .UR
    0.06
    20
    0.06
     Perm
    0.06
     exceeds
    0.06
    //------------------------------------------------------------------------------↵
    0.06
    @return
    0.06
    //------------------------------------------------------------------------------------------------
    0.06
     Nir
    0.06
    Activations Density 0.011%

    No Known Activations