© 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. 125202
    Prev
    Next
    INDEX
    Explanations

    catch

    np_max-act · gemini-2.0-flash

    text relating to error handling in programming.

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

    The neuron detects terminology related to exception‐handling constructs (e.g. “catch,” “except,” and “handling”).

    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
     cancellationToken
    -0.07
    CustomerId
    -0.07
    _SECOND
    -0.06
     gigs
    -0.06
     loading
    -0.06
    温
    -0.06
    Binary
    -0.06
     Strip
    -0.06
     invocation
    -0.06
     boarding
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    icken
    0.07
    گونه
    0.06
    edla
    0.06
    mong
    0.06
    .setStyle
    0.06
     depressed
    0.06
    Ｅ
    0.06
    าผ
    0.06
    _outline
    0.06
    Activations Density 0.008%

    No Known Activations