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. 15-RESID-POST-AA
    6. 111227
    Prev
    Next
    INDEX
    Explanations

    for

    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
     σχε
    -0.07
     Doe
    -0.06
     bike
    -0.06
    >>
    -0.06
     ")
    -0.06
    狐
    -0.05
     Strategy
    -0.05
     emitter
    -0.05
    ”),
    -0.05
     hal
    -0.05
    POSITIVE LOGITS
    (steps
    0.08
    문제
    0.07
     columnIndex
    0.07
    ?url
    0.06
    _SPELL
    0.06
    abama
    0.06
     serão
    0.06
    [OF
    0.06
     Psr
    0.06
     spir
    0.06
    Activations Density 0.030%

    No Known Activations