© 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
    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. 55803
    Prev
    Next
    INDEX
    Explanations

    dial

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens relating to “dialysis,” including its various forms and derivatives (e.g., dialysate, dialyzer, hemofiltration).

    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
    cluded
    -0.08
    Kr
    -0.07
    وح
    -0.07
    companies
    -0.07
    ulet
    -0.06
    gro
    -0.06
    GRE
    -0.06
    UST
    -0.06
    OMEM
    -0.06
    ekt
    -0.06
    POSITIVE LOGITS
     dial
    0.14
     Dial
    0.12
    adjust
    0.08
     spiral
    0.07
    designation
    0.07
    Labels
    0.07
    xo
    0.07
    ial
    0.06
     Dipl
    0.06
    459
    0.06
    Activations Density 0.003%

    No Known Activations