© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 102630
    Prev
    Next
    INDEX
    Explanations

    scam warnings/discussions

    np_max-act · gemini-2.0-flash

    potentially harmful or manipulative intents in conversations.

    oai_token-act-pair · gpt-4o-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
    .ts
    -0.08
     referrals
    -0.07
     Method
    -0.07
    _blob
    -0.06
    _PRESS
    -0.06
     müz
    -0.06
     manner
    -0.06
    NotNil
    -0.06
    doesn
    -0.06
     Nights
    -0.06
    POSITIVE LOGITS
    .githubusercontent
    0.06
    .getConnection
    0.06
    lsru
    0.06
     trí
    0.06
    .Rect
    0.06
     SSL
    0.06
     τό
    0.06
    ventus
    0.06
    alamat
    0.06
    mania
    0.06
    Activations Density 0.005%

    No Known Activations