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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 80754
    Prev
    Next
    INDEX
    Explanations

    :=

    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_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
     výzkum
    -0.07
    Sand
    -0.07
     kategor
    -0.07
     Activity
    -0.06
    THR
    -0.06
    tr
    -0.06
    udd
    -0.06
    dro
    -0.06
    ustomer
    -0.06
    projects
    -0.06
    POSITIVE LOGITS
     :=
    0.10
    AWN
    0.08
    :=
    0.08
    ien
    0.08
    iện
    0.08
    ::::::::::::::::::::::::::::::::
    0.07
    封
    0.07
    ***/↵↵
    0.07
     сдел
    0.07
    lice
    0.07
    Activations Density 0.006%

    No Known Activations