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. 23-RESID-POST-AA
    6. 103620
    Prev
    Next
    INDEX
    Explanations

    't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Î
    -0.07
     reasons
    -0.06
     meisjes
    -0.06
    .Runtime
    -0.06
    경기
    -0.06
    öm
    -0.06
     eye
    -0.06
    .TimeUnit
    -0.06
    Domain
    -0.06
     material
    -0.06
    POSITIVE LOGITS
    lassen
    0.07
    .listeners
    0.06
    інь
    0.06
    HQ
    0.06
    ši
    0.06
    alesce
    0.06
    _ASS
    0.06
    افر
    0.06
     negligent
    0.06
    .dot
    0.06
    Activations Density 0.023%

    No Known Activations