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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26112
    Prev
    Next
    INDEX
    Explanations

    (= is

    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
    оте
    -0.07
     McCarthy
    -0.06
    USED
    -0.06
    CLU
    -0.06
    zę
    -0.06
     continuum
    -0.06
     Cooke
    -0.06
    uilt
    -0.06
     सर
    -0.06
     summaries
    -0.06
    POSITIVE LOGITS
     rss
    0.07
    .startTime
    0.06
    ."/
    0.06
     обычно
    0.06
     hiking
    0.06
     salv
    0.06
     рез
    0.06
    _reporting
    0.06
    Iterator
    0.06
    (pass
    0.06
    Activations Density 0.003%

    No Known Activations