Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 55274
    Prev
    Next
    INDEX
    Explanations

    Code/programming snippets

    np_max-act · gemini-2.0-flash

    The neuron preferentially activates on floating‐point numeric literals (decimal numbers) in the text.

    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
    -invalid
    -0.07
     MUST
    -0.07
     address
    -0.06
    cence
    -0.06
    .yang
    -0.06
    RESS
    -0.06
    forth
    -0.06
     Copy
    -0.06
    utos
    -0.06
     Girlfriend
    -0.06
    POSITIVE LOGITS
     đ
    0.07
    "]="
    0.06
     Hacker
    0.06
    (win
    0.06
     Xi
    0.06
     Gregg
    0.06
     Color
    0.06
    Fine
    0.06
     Trinity
    0.06
     webcam
    0.06
    Activations Density 0.007%

    No Known Activations