© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126241
    Prev
    Next
    INDEX
    Explanations

    academic text

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and measurements (dates, counts, word‐length limits, chapter/section numbers, etc.).

    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
    _file
    -0.07
    Sel
    -0.07
     biscuits
    -0.07
    SRC
    -0.06
     mistress
    -0.06
     HttpResponse
    -0.06
    Bubble
    -0.06
     horns
    -0.06
    tick
    -0.06
    EA
    -0.06
    POSITIVE LOGITS
     그렇
    0.06
    ConnectionString
    0.06
     fifty
    0.06
    	freopen
    0.06
    .MILLISECONDS
    0.06
     شركة
    0.06
     EINA
    0.06
     "-//
    0.06
     GetString
    0.06
     ід
    0.06
    Activations Density 0.060%

    No Known Activations