© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42723
    Prev
    Next
    INDEX
    Explanations

    start low and gradually

    np_max-act · gemini-2.0-flash

    The neuron detects words that signal gradual, step-by-step progression or cautious increase (e.g. “start,” “slowly,” “gradually,” “increase”).

    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
     Nazis
    -0.07
     нап
    -0.06
     Mountains
    -0.06
     freeze
    -0.06
     Macron
    -0.06
    โย
    -0.06
    Netflix
    -0.06
     frying
    -0.06
    	now
    -0.06
     riot
    -0.06
    POSITIVE LOGITS
    نتی
    0.07
     بازبینی
    0.07
    фік
    0.07
    ypical
    0.07
     pří
    0.07
     Ellis
    0.06
    WP
    0.06
    olución
    0.06
     ```
    0.06
    )',
    0.06
    Activations Density 0.007%

    No Known Activations