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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 89012
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron detects tokens from the boilerplate instruction header—especially the phrase specifying “Input is from a news article.”

    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
    //
    -0.07
    vg
    -0.06
    waitFor
    -0.06
    btn
    -0.06
    aversal
    -0.06
    ूप
    -0.06
    ereço
    -0.06
     proprietary
    -0.06
    oded
    -0.06
    ipeline
    -0.06
    POSITIVE LOGITS
    /category
    0.08
     experimented
    0.07
     transport
    0.06
    ments
    0.06
    豆
    0.06
    ????
    0.06
    :'.$
    0.06
    .ERR
    0.06
     edil
    0.06
    lanmış
    0.06
    Activations Density 0.002%

    No Known Activations