© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25861
    Prev
    Next
    INDEX
    Explanations

    interesting

    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
     jerk
    -0.07
    شناس
    -0.06
    _HANDLE
    -0.06
    AttributeValue
    -0.06
     Luc
    -0.06
    595
    -0.06
     rotten
    -0.06
    "urls
    -0.06
     jó
    -0.06
    Pie
    -0.06
    POSITIVE LOGITS
     dbg
    0.07
     interesting
    0.07
     bara
    0.06
     sandy
    0.06
    ρίς
    0.06
     homosexuals
    0.06
    UTDOWN
    0.06
     studies
    0.06
    previous
    0.06
     Ц
    0.06
    Activations Density 0.058%

    No Known Activations