Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 105987
    Prev
    Next
    INDEX
    Explanations

    people's names

    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_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
    Tcp
    -0.07
    .Combine
    -0.07
    .isNullOrEmpty
    -0.07
    umes
    -0.06
    	Response
    -0.06
    _CONF
    -0.06
    uni
    -0.06
     threadIdx
    -0.06
    ibilit
    -0.06
     LatLng
    -0.06
    POSITIVE LOGITS
     mys
    0.06
    /build
    0.06
    _REAL
    0.06
    (identifier
    0.06
    _grade
    0.06
    _finish
    0.06
     rosa
    0.06
    ]';↵
    0.06
    (arr
    0.06
    gg
    0.06
    Activations Density 0.073%

    No Known Activations