© 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. 89599
    Prev
    Next
    INDEX
    Explanations

    Histology and tissue repair

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptions of experimental outcome measures—especially phrases about forming, generating, preserving, or increasing new tissue (e.g. “formation of new tissue,” “volume preservation,” “functional tissue”).

    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
    -archive
    -0.07
     cp
    -0.07
     toes
    -0.07
    109
    -0.06
     reaction
    -0.06
     Builds
    -0.06
    節
    -0.06
    yah
    -0.06
     Paul
    -0.06
    스를
    -0.06
    POSITIVE LOGITS
    .getPassword
    0.07
    _vector
    0.07
    _TRANSFORM
    0.06
     linebacker
    0.06
     represent
    0.06
     :↵
    0.06
    "]↵
    0.06
     домаш
    0.06
    emez
    0.06
    τρι
    0.06
    Activations Density 0.032%

    No Known Activations