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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 122865
    Prev
    Next
    INDEX
    Explanations

    magazines and publications

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.06
    +len
    -0.06
    iosis
    -0.06
     вона
    -0.06
    .annotation
    -0.06
     mw
    -0.06
    [code
    -0.06
     looked
    -0.06
     AMA
    -0.06
    readOnly
    -0.06
    POSITIVE LOGITS
     Gazette
    0.08
     journal
    0.08
    >manual
    0.07
    ulos
    0.07
     Digest
    0.07
    alter
    0.06
    雑
    0.06
    acular
    0.06
     Dense
    0.06
    elage
    0.06
    Activations Density 0.026%

    No Known Activations