© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 47164
    Prev
    Next
    INDEX
    Explanations

    α

    np_max-act · gemini-2.0-flash

    instances of the Greek letter α when used as a suffix on molecule/cytokine names.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ету
    -0.07
    .getStart
    -0.07
     Returns
    -0.07
     dying
    -0.07
     meses
    -0.07
    али
    -0.06
     oder
    -0.06
    %"
    -0.06
     предлож
    -0.06
    ]]
    -0.06
    POSITIVE LOGITS
    -seat
    0.07
    ,q
    0.07
    <Float
    0.06
    _config
    0.06
     примі
    0.06
    辅
    0.06
     Cumhurbaş
    0.06
    /Q
    0.06
     标
    0.06
    _TC
    0.06
    Activations Density 0.002%

    No Known Activations