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. 76210
    Prev
    Next
    INDEX
    Explanations

    forward/forth

    np_max-act · gemini-2.0-flash

    expressions of admiration or critique regarding public figures and their influence on politics.

    oai_token-act-pair · gpt-4o-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
     tooth
    -0.07
    роничес
    -0.07
    (){↵↵
    -0.07
     patched
    -0.06
     ripping
    -0.06
     ensures
    -0.06
     WCHAR
    -0.06
     interpreted
    -0.06
     amazed
    -0.06
     mafia
    -0.06
    POSITIVE LOGITS
     مف
    0.07
    WX
    0.06
    _adv
    0.06
     no
    0.06
    stacles
    0.06
    (idx
    0.06
     altern
    0.06
     ô
    0.06
     ascend
    0.06
     Responsibility
    0.06
    Activations Density 0.026%

    No Known Activations