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. 38925
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ラック
    -0.07
    Mouse
    -0.07
    _updated
    -0.06
     buurt
    -0.06
     terminate
    -0.06
    _ax
    -0.06
     Marble
    -0.06
    118
    -0.06
    ū
    -0.06
    clusters
    -0.06
    POSITIVE LOGITS
    �
    0.07
     зрения
    0.07
    AxisSize
    0.07
     IST
    0.07
     واحدة
    0.07
     ワ
    0.06
    нить
    0.06
     δε
    0.06
    _POSITION
    0.06
    RESH
    0.06
    Activations Density 0.074%

    No Known Activations