© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 108683
    Prev
    Next
    INDEX
    Explanations

    70

    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
     diary
    -0.07
     Math
    -0.07
    ONTAL
    -0.07
     fictional
    -0.06
     nef
    -0.06
    _the
    -0.06
     vouchers
    -0.06
     nal
    -0.06
    -video
    -0.06
     Corm
    -0.06
    POSITIVE LOGITS
    60
    0.11
    71
    0.11
    72
    0.10
    70
    0.10
    66
    0.10
    62
    0.09
    65
    0.09
    59
    0.09
    68
    0.09
    58
    0.09
    Activations Density 0.073%

    No Known Activations