© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7133
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to code-formatting markers (e.g. backticks and fence delimiters) rather than natural‐language tokens.

    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
    .Values
    -0.07
    alking
    -0.06
    имо
    -0.06
     languages
    -0.06
    “If
    -0.06
    _WIDTH
    -0.06
    .RIGHT
    -0.06
     verified
    -0.06
    _SIGNAL
    -0.05
    ),
    -0.05
    POSITIVE LOGITS
    ึ้
    0.07
    _variance
    0.07
     retrofit
    0.07
    District
    0.06
     kez
    0.06
     suggestive
    0.06
     finale
    0.06
     plotting
    0.06
     powerless
    0.06
     ActionBar
    0.06
    Activations Density 0.020%

    No Known Activations