© 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. 11-RESID-POST-AA
    6. 42663
    Prev
    Next
    INDEX
    Explanations

    pulp

    np_max-act · gemini-2.0-flash

    the word “pulp” and its variants (e.g. pulping) in discussions of paper or pulp processing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ████
    -0.07
     хроничес
    -0.07
    Alamat
    -0.06
     τρό
    -0.06
    Min
    -0.06
    immutable
    -0.06
     Roths
    -0.06
    imální
    -0.06
     mezun
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     pulp
    0.11
    ulp
    0.10
     pomp
    0.07
    upd
    0.07
    При
    0.07
     위
    0.07
     Ups
    0.07
    =view
    0.07
    -app
    0.07
     Prim
    0.06
    Activations Density 0.001%

    No Known Activations