© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 41903
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ौड
    -0.07
    (Route
    -0.06
    (document
    -0.06
     Dysfunction
    -0.06
    _encrypt
    -0.06
    NCY
    -0.06
     العربي
    -0.06
    ゞ
    -0.06
     decorative
    -0.06
     chmod
    -0.06
    POSITIVE LOGITS
     sensible
    0.07
     creating
    0.07
    persistent
    0.06
     screened
    0.06
     uninsured
    0.06
     absorption
    0.06
    supports
    0.06
    normalized
    0.06
    acked
    0.06
     noticeably
    0.06
    Activations Density 0.001%

    No Known Activations