© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29954
    Prev
    Next
    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash

    complex mathematical concepts and their proofs.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on occurrences of the verb “find” (especially in instructional or objective phrases like “to find…”).

    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
     Dragons
    -0.07
     magically
    -0.07
     impl
    -0.06
    (ref
    -0.06
    (in
    -0.06
     uydu
    -0.06
    worthy
    -0.06
     scarcity
    -0.06
    REC
    -0.06
     uy
    -0.06
    POSITIVE LOGITS
    .toJSONString
    0.07
    _confirm
    0.06
    http
    0.06
    �
    0.06
    "profile
    0.06
     özg
    0.06
    copyright
    0.06
    细胞
    0.06
    master
    0.06
     百
    0.06
    Activations Density 0.082%

    No Known Activations