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. 27-RESID-POST-AA
    6. 102121
    Prev
    Next
    INDEX
    Explanations

    Accounting and Finance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIR
    -0.07
    omor
    -0.07
     produce
    -0.06
    inning
    -0.06
     anchor
    -0.06
     above
    -0.06
    42
    -0.06
    undef
    -0.06
     associative
    -0.06
    彼
    -0.06
    POSITIVE LOGITS
     vmax
    0.07
     souvis
    0.06
    (clazz
    0.06
    _rad
    0.06
     pois
    0.06
    _cuda
    0.06
     CLLocationCoordinate
    0.06
     Τι
    0.06
    ▍
    0.06
    .sid
    0.06
    Activations Density 0.019%

    No Known Activations