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. 15-RESID-POST-AA
    6. 27891
    Prev
    Next
    INDEX
    Explanations

    me

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (ci
    -0.07
    .cy
    -0.06
    otive
    -0.06
     ceremonial
    -0.06
     settle
    -0.06
     expl
    -0.06
     assaults
    -0.06
     intentional
    -0.06
    ขาย
    -0.06
    ases
    -0.06
    POSITIVE LOGITS
    ’n
    0.07
    _BTN
    0.07
    UBLE
    0.06
     Belly
    0.06
    _##
    0.06
     bytesRead
    0.06
    (Base
    0.06
    ?option
    0.06
     стара
    0.06
    _Table
    0.06
    Activations Density 0.012%

    No Known Activations