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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6920
    Prev
    Next
    INDEX
    Explanations

    kidney

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of kidney‐related terms, especially “renal” and closely associated concepts (e.g., renal excretion or renal function).

    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
     caves
    -0.08
     markings
    -0.07
    -era
    -0.07
    -car
    -0.06
     directors
    -0.06
     Crist
    -0.06
    -com
    -0.06
    .dat
    -0.06
    Side
    -0.06
    FONT
    -0.06
    POSITIVE LOGITS
    ‌د
    0.07
    defs
    0.07
    /place
    0.07
    $("#
    0.06
    _strlen
    0.06
     grief
    0.06
    (il
    0.06
    _dr
    0.06
     vois
    0.06
     Alexis
    0.06
    Activations Density 0.022%

    No Known Activations