Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 108656
    Prev
    Next
    INDEX
    Explanations

    underwear

    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
    _ctr
    -0.07
     daemon
    -0.06
     streaming
    -0.06
     slew
    -0.06
     多
    -0.06
     toned
    -0.06
    OTOR
    -0.06
     द
    -0.06
     Horizon
    -0.06
    Off
    -0.06
    POSITIVE LOGITS
    emade
    0.08
    :Any
    0.07
     underwear
    0.07
    agen
    0.07
    izarre
    0.07
    appiness
    0.06
    ENTIC
    0.06
    :url
    0.06
    ellery
    0.06
     недел
    0.06
    Activations Density 0.008%

    No Known Activations