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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54108
    Prev
    Next
    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    tokens representing numbers or numeric values.

    oai_token-act-pair · gpt-5-miniTriggered by @bowenyi
    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
     satire
    -0.08
     Platforms
    -0.07
     addressed
    -0.07
    ительства
    -0.06
    /st
    -0.06
    าษ
    -0.06
    ชาย
    -0.06
    ']),
    -0.06
     노출
    -0.06
    )!
    -0.06
    POSITIVE LOGITS
    TexImage
    0.07
    NTAX
    0.07
    FRAME
    0.07
    detalle
    0.06
     تن
    0.06
    ATA
    0.06
    "log
    0.06
    Bitcoin
    0.06
    养
    0.06
    ažd
    0.06
    Activations Density 0.042%

    No Known Activations