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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95715
    Prev
    Next
    INDEX
    Explanations

    how

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _fix
    -0.06
    _ball
    -0.06
    }}>
    -0.06
     이벤트
    -0.06
     cooldown
    -0.06
    }>
    -0.06
     ورز
    -0.06
     }}>
    -0.06
    =\
    -0.06
     Protestant
    -0.06
    POSITIVE LOGITS
     Con
    0.06
    /rfc
    0.06
    -chain
    0.06
    ddie
    0.06
     how
    0.06
     pdb
    0.06
    ãy
    0.06
     Immun
    0.06
     hops
    0.06
    _SWITCH
    0.06
    Activations Density 0.038%

    No Known Activations