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. 128941
    Prev
    Next
    INDEX
    Explanations

    :

    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
    PLICATION
    -0.06
     Вал
    -0.06
    Given
    -0.06
    -used
    -0.06
    .svg
    -0.06
    -learning
    -0.06
    Lang
    -0.06
    -fold
    -0.06
    Donald
    -0.06
     Werk
    -0.06
    POSITIVE LOGITS
    (UINT
    0.07
    (@(
    0.07
    ])**
    0.07
    ))*
    0.07
    '].$
    0.07
     chia
    0.07
    ;z
    0.07
    '"
    0.06
    .Exists
    0.06
    ("+
    0.06
    Activations Density 0.021%

    No Known Activations