© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 87647
    Prev
    Next
    INDEX
    Explanations

    And

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buddies
    -0.06
    azo
    -0.06
     formerly
    -0.06
    *r
    -0.06
     furry
    -0.06
    '''
    -0.06
    ее
    -0.06
     причина
    -0.06
    _execute
    -0.06
    wipe
    -0.06
    POSITIVE LOGITS
    ._
    0.08
    And
    0.07
    .And
    0.07
     And
    0.07
    .Adam
    0.06
    (term
    0.06
     Và
    0.06
     Chan
    0.06
     ))↵↵
    0.06
     dang
    0.06
    Activations Density 0.041%

    No Known Activations