© 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. 25954
    Prev
    Next
    INDEX
    Explanations

    your path

    np_max-act · gemini-2.0-flash

    references to media or creative content, specifically focusing on questions or discussions about films and programming solutions involving file handling.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron never activates on any tokens—it appears to be effectively “dead” and does not detect any pattern.

    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
    localObject
    -0.07
     mening
    -0.06
     emph
    -0.06
     सत
    -0.06
    _HTML
    -0.06
    pecific
    -0.06
    �
    -0.06
     Ses
    -0.06
    $count
    -0.06
     ETF
    -0.06
    POSITIVE LOGITS
    Tweet
    0.07
    也是
    0.06
     Gaut
    0.06
    ению
    0.06
    SerializeField
    0.06
     Blair
    0.06
     Constant
    0.06
     Nature
    0.06
     FIFA
    0.06
     мере
    0.06
    Activations Density 0.050%

    No Known Activations