© 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. 109466
    Prev
    Next
    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash

    The neuron fires on the “from” and “for” keywords used as slice‐bound specifiers (e.g. in substring(...) calls).

    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
     marginTop
    -0.07
    Recipient
    -0.07
     Cand
    -0.07
     Sanchez
    -0.07
    aste
    -0.07
    idente
    -0.07
    (Util
    -0.07
     Technology
    -0.07
    .numero
    -0.06
    Britain
    -0.06
    POSITIVE LOGITS
    ']),
    0.07
     quarry
    0.07
     spoken
    0.07
    <<(
    0.07
     worth
    0.07
    (random
    0.07
     keto
    0.06
    [],
    0.06
     asympt
    0.06
    .ta
    0.06
    Activations Density 0.020%

    No Known Activations