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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 91571
    Prev
    Next
    INDEX
    Explanations

    technical design and writing

    np_max-act · gemini-2.0-flash

    The neuron detects parts of floating‐point numbers (decimal tokens).

    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
    ++)↵
    -0.06
    .getData
    -0.06
    !")↵
    -0.06
    )");
    ↵
    -0.06
     (!!
    -0.06
     متح
    -0.06
    cxx
    -0.06
    -containing
    -0.06
    ाऊ
    -0.06
     Api
    -0.06
    POSITIVE LOGITS
    Queryable
    0.07
     shrugged
    0.07
    Para
    0.06
    oras
    0.06
    walker
    0.06
    ***/↵↵
    0.06
    _SERIAL
    0.06
    &p
    0.06
    _BS
    0.06
    Phase
    0.06
    Activations Density 0.159%

    No Known Activations