© 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. 15-RESID-POST-AA
    6. 109494
    Prev
    Next
    INDEX
    Explanations

    technical instructions/answers

    np_max-act · gemini-2.0-flash

    Detects user requests for instructions, links, or assistance that facilitate illegal, harmful, or policy-disallowed activities.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     устанавлива
    -0.07
     ем
    -0.07
    amine
    -0.06
     Palmer
    -0.06
    Explicit
    -0.06
    _usr
    -0.06
    perf
    -0.06
     Richie
    -0.06
     therm
    -0.06
     criminals
    -0.06
    POSITIVE LOGITS
     gu
    0.07
     hâlâ
    0.06
    FRINGEMENT
    0.06
    εις
    0.06
    'é
    0.06
     LSM
    0.06
    ACHINE
    0.06
    ease
    0.06
    .Me
    0.06
    .getMessage
    0.06
    Activations Density 0.112%

    No Known Activations