© 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. 41677
    Prev
    Next
    INDEX
    Explanations

    derivative

    np_max-act · gemini-2.0-flash

    This neuron fires most strongly on the floating‐point numbers that annotate derivative values (e.g. “4.66015625”) in the math text.

    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
    contre
    -0.06
     adulthood
    -0.06
    _By
    -0.06
     RETURN
    -0.06
    _EL
    -0.06
     하면
    -0.06
    ْن
    -0.06
    (post
    -0.06
     Gins
    -0.06
     ad
    -0.06
    POSITIVE LOGITS
     StringBuilder
    0.07
     sildenafil
    0.06
    ,被
    0.06
    ি�
    0.06
     Elite
    0.06
     Kov
    0.06
    .getFloat
    0.06
    (Process
    0.06
     сильно
    0.06
     Backup
    0.06
    Activations Density 0.001%

    No Known Activations