© 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. 42545
    Prev
    Next
    INDEX
    Explanations

    C variable types

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numeric literals (numbers with decimal points) in the code.

    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
    電影
    -0.07
    .readValue
    -0.06
    _depth
    -0.06
    cw
    -0.06
    association
    -0.06
    _IO
    -0.06
    _TRUNC
    -0.06
     adversaries
    -0.06
    ंदर
    -0.06
    ),"
    -0.06
    POSITIVE LOGITS
     Beckham
    0.07
     Metals
    0.06
     injust
    0.06
     countered
    0.06
    编
    0.06
     Brisbane
    0.06
     zam
    0.06
    .isValid
    0.05
     Arsenal
    0.05
    :number
    0.05
    Activations Density 0.017%

    No Known Activations