© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 112065
    Prev
    Next
    INDEX
    Explanations

    code

    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
     ль
    -0.07
     tide
    -0.06
    _Rem
    -0.06
     指
    -0.06
     unicorn
    -0.06
    改变
    -0.06
     posição
    -0.06
    Tar
    -0.06
     expiration
    -0.06
    лод
    -0.06
    POSITIVE LOGITS
    LIC
    0.07
     accompagn
    0.07
    ispens
    0.06
    .PropTypes
    0.06
     sieht
    0.06
    SPATH
    0.06
     BW
    0.06
    Neutral
    0.06
     rankings
    0.06
    adena
    0.06
    Activations Density 0.003%

    No Known Activations