© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92149
    Prev
    Next
    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the keyword “static” (often in function declarations).

    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
     στο
    -0.06
     propaganda
    -0.06
     couple
    -0.06
    ility
    -0.06
     بأ
    -0.06
     curt
    -0.06
     accommodation
    -0.06
    σίας
    -0.05
    'O
    -0.05
    -left
    -0.05
    POSITIVE LOGITS
     priceless
    0.07
     Invoice
    0.07
     boldly
    0.07
     Ri
    0.07
     Donovan
    0.07
    REG
    0.06
    (Runtime
    0.06
     exploding
    0.06
     Amber
    0.06
    стер
    0.06
    Activations Density 0.011%

    No Known Activations