© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 25525
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    mentions of system/software requirements, functionality, and technical components (e.g., system names, modules, users, and database/feature terms).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    VertexAttrib
    -0.07
    getClass
    -0.07
    (Rect
    -0.07
     disap
    -0.06
    Rated
    -0.06
    zc
    -0.06
    .Inv
    -0.06
    (shape
    -0.06
    _barrier
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     e
    0.09
     playing
    0.07
    ël
    0.07
    -se
    0.06
    ski
    0.06
     factory
    0.06
     against
    0.06
    相同
    0.06
     synd
    0.06
    _fraction
    0.06
    Activations Density 31.984%

    No Known Activations