© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 88939
    Prev
    Next
    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash

    chemical compounds and their relationships in production processes.

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

    This neuron detects numeric positional descriptors in chemical names (e.g. “(1H,3H)-” and similar numbered annotations).

    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
     Roger
    -0.07
    �
    -0.07
     retract
    -0.06
     wages
    -0.06
     ACL
    -0.06
     NP
    -0.06
    _df
    -0.06
    ΑΝ
    -0.06
     cycling
    -0.06
     bốn
    -0.06
    POSITIVE LOGITS
    는지
    0.06
    usable
    0.06
    .layoutControl
    0.06
     momentarily
    0.06
     mom
    0.06
     mainScreen
    0.06
    дают
    0.06
    (Task
    0.06
    Submitting
    0.06
     freeing
    0.06
    Activations Density 0.012%

    No Known Activations