© 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. 125940
    Prev
    Next
    INDEX
    Explanations

    Log

    np_max-act · gemini-2.0-flash

    The neuron fires on any occurrence of the substring “log” (e.g. “Log,” “log,” “login,” 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
    Merchant
    -0.08
     craz
    -0.08
     aunt
    -0.07
     Σεπ
    -0.07
     Barton
    -0.07
    erta
    -0.07
     faction
    -0.07
     Seven
    -0.07
     Freund
    -0.07
    ienza
    -0.07
    POSITIVE LOGITS
    log
    0.13
     log
    0.13
    Log
    0.13
     Log
    0.11
     logs
    0.11
    LogFile
    0.11
    _log
    0.10
     LOG
    0.10
    	log
    0.10
    .Logging
    0.10
    Activations Density 0.032%

    No Known Activations