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. 221
    Prev
    Next
    INDEX
    Explanations

    bone and tissue growth

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to terms referring to bone and bone‐growth or bone‐tissue integration.

    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
     dbname
    -0.07
    aversal
    -0.06
    _BAR
    -0.06
     Weinstein
    -0.06
    етич
    -0.06
    _audio
    -0.06
    Voltage
    -0.06
    .coord
    -0.06
     Marcos
    -0.06
     Stout
    -0.06
    POSITIVE LOGITS
    Should
    0.07
    expl
    0.07
     ]↵
    0.07
    ?↵↵
    0.06
    입
    0.06
     رق
    0.06
    //{↵
    0.06
     læ
    0.06
     triang
    0.06
     handc
    0.06
    Activations Density 0.014%

    No Known Activations