© 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. 126193
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    The neuron fires on words that serve as reasoning or explanation cues—i.e. discourse markers like “Step,” “However,” “Note,” and “Explanation”—flagging segments of analytical or step‐by‐step commentary.

    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
    .AreEqual
    -0.06
    compareTo
    -0.06
     Dome
    -0.06
    	title
    -0.06
     deceive
    -0.06
    	object
    -0.06
     Buzz
    -0.06
     الکترون
    -0.06
     cpt
    -0.06
    instanc
    -0.06
    POSITIVE LOGITS
     inventive
    0.07
    PELL
    0.06
     EVP
    0.06
     YY
    0.06
    iatric
    0.06
    رف
    0.06
    �
    0.06
    ницип
    0.06
    ["+
    0.06
     ￥
    0.06
    Activations Density 0.123%

    No Known Activations