© 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. 85792
    Prev
    Next
    INDEX
    Explanations

    defects, errors

    np_max-act · gemini-2.0-flash

    The neuron is triggered by terms denoting faults, errors, or undesirable conditions (e.g., downtime, defects, imperfections, tear, rust).

    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
    örper
    -0.07
    serialization
    -0.07
     vero
    -0.07
    sten
    -0.07
     Empty
    -0.06
     Ιω
    -0.06
    imap
    -0.06
    	break
    -0.06
    [indexPath
    -0.06
     digits
    -0.06
    POSITIVE LOGITS
    _CHILD
    0.06
     LARGE
    0.06
    .ll
    0.06
    -parent
    0.06
     ince
    0.06
     attached
    0.06
    .HtmlControls
    0.06
    tools
    0.06
    /math
    0.06
     ranger
    0.06
    Activations Density 0.090%

    No Known Activations