© 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
    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. 43467
    Prev
    Next
    INDEX
    Explanations

    harmless

    np_max-act · gemini-2.0-flash

    The neuron fires on legal‐opinion phrasing that discusses trial‐court error and whether it was harmless.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    't
    -0.07
    _short
    -0.07
    ’t
    -0.07
     podí
    -0.06
    เลย
    -0.06
     jestli
    -0.06
    _PT
    -0.06
    radient
    -0.06
     ฮ
    -0.06
     evoke
    -0.06
    POSITIVE LOGITS
    !”↵↵
    0.06
    .loader
    0.06
    %.↵
    0.06
     )}↵
    0.06
    %",↵
    0.06
    /thumb
    0.06
     Blaze
    0.06
    ?”↵↵
    0.06
     halinde
    0.06
    .Pages
    0.06
    Activations Density 0.005%

    No Known Activations