© 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. 4957
    Prev
    Next
    INDEX
    Explanations

    with

    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
    .')
    -0.07
    _marshaled
    -0.06
    ]);
    -0.06
     Zum
    -0.06
     vem
    -0.06
     JOHN
    -0.06
     fuzzy
    -0.06
     splash
    -0.06
     deniz
    -0.06
    _TRANSACTION
    -0.06
    POSITIVE LOGITS
    -media
    0.07
    _LABEL
    0.07
     CONTRIBUTORS
    0.06
     severity
    0.06
    enabled
    0.06
     desc
    0.06
    measure
    0.06
    ertiary
    0.06
     electronically
    0.06
    <html
    0.06
    Activations Density 0.470%

    No Known Activations