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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9072
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron is primarily responding to tokens that represent floating‐point numbers.

    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
    .Args
    -0.07
    -wsj
    -0.07
    Transformation
    -0.06
     Souls
    -0.06
    >Note
    -0.06
    Invocation
    -0.06
    _lr
    -0.06
    Rooms
    -0.06
     coefficients
    -0.06
    _POLICY
    -0.06
    POSITIVE LOGITS
    perform
    0.06
     لت
    0.06
     nhạc
    0.06
    _btn
    0.06
    }(
    0.06
    ように
    0.06
    ,却
    0.06
     Screen
    0.06
    }{
    0.06
     Г
    0.06
    Activations Density 0.037%

    No Known Activations