Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125850
    Prev
    Next
    INDEX
    Explanations

    factoring out

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens signaling algebraic manipulation steps—words like “factor,” “out,” “cancel,” “simplify,” “divide,” and similar indicators of transforming or rearranging an equation.

    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
     strong
    -0.07
     Strong
    -0.07
     saldır
    -0.06
     butterfly
    -0.06
    Playable
    -0.06
    _costs
    -0.06
    gradient
    -0.06
     подіб
    -0.06
    frame
    -0.06
     blocks
    -0.06
    POSITIVE LOGITS
     للإ
    0.07
     ради
    0.07
    Fed
    0.06
     masse
    0.06
     issuance
    0.06
    险
    0.06
    (enum
    0.06
    .redis
    0.06
    。
    ↵
    0.06
    omez
    0.06
    Activations Density 0.008%

    No Known Activations