Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25527
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    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
    ัต
    -0.07
     euler
    -0.07
     deployed
    -0.06
    _FAILURE
    -0.06
    Invoke
    -0.06
     Sunset
    -0.06
    陶
    -0.06
     famously
    -0.06
    _log
    -0.06
    -plus
    -0.06
    POSITIVE LOGITS
    ivatel
    0.07
    alertView
    0.07
    \HttpFoundation
    0.07
     rámci
    0.06
     Lös
    0.06
    Component
    0.06
     pourquoi
    0.06
    <src
    0.06
    [string
    0.06
    lc
    0.06
    Activations Density 0.069%

    No Known Activations