© 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. 126589
    Prev
    Next
    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash

    This neuron fires on the instruction phrase “Collect the terms in,” especially on the word “terms” (and its neighbors “the” and “in”).

    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
    -design
    -0.08
     zap
    -0.07
    /fl
    -0.07
     Flint
    -0.07
    Semaphore
    -0.07
     เซ
    -0.07
     inp
    -0.07
     Import
    -0.07
    -close
    -0.06
    _calls
    -0.06
    POSITIVE LOGITS
    asi
    0.06
    (Html
    0.06
    :nth
    0.06
     muestra
    0.06
     hük
    0.06
    <source
    0.05
    чої
    0.05
     Çünkü
    0.05
    ınca
    0.05
     constituent
    0.05
    Activations Density 0.005%

    No Known Activations