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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6381
    Prev
    Next
    INDEX
    Explanations

    illegal, law

    np_max-act · gemini-2.0-flash

    Instances mentioning illegal, dangerous, or criminal activities (words signaling illegality/unauthorized or safety/policy refusals).

    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
    _tracker
    -0.08
    .enemy
    -0.08
    _Msg
    -0.07
     prer
    -0.07
    şı
    -0.07
     hawk
    -0.07
    _IB
    -0.07
    Damage
    -0.06
     кв
    -0.06
     trouvé
    -0.06
    POSITIVE LOGITS
    GTK
    0.07
     Jerry
    0.07
     shoot
    0.07
     regardless
    0.06
     collar
    0.06
    aving
    0.06
    Victoria
    0.06
     Brunswick
    0.06
     v
    0.06
    enter
    0.06
    Activations Density 0.021%

    No Known Activations