© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 39436
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Manga
    -0.07
     flows
    -0.07
     survival
    -0.06
     MAL
    -0.06
     Cause
    -0.06
    "..
    -0.06
    摸
    -0.06
     substitutions
    -0.06
     recurs
    -0.06
    Wind
    -0.06
    POSITIVE LOGITS
    prim
    0.07
    aside
    0.07
    Impl
    0.06
    _oc
    0.06
    Difficulty
    0.06
    ère
    0.06
     =================================================================
    0.06
    лам
    0.06
    ках
    0.06
    Lista
    0.06
    Activations Density 0.035%

    No Known Activations