© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91477
    Prev
    Next
    INDEX
    Explanations

    medical testing

    np_max-act · gemini-2.0-flash

    The neuron detects numeric measurements or quantitative values (including decimals, time durations, and units).

    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
     outputs
    -0.07
    “Yes
    -0.06
    839
    -0.06
    shake
    -0.06
    NER
    -0.06
     τε
    -0.06
    _te
    -0.06
     harmonic
    -0.06
    git
    -0.06
     karma
    -0.06
    POSITIVE LOGITS
    /',
    0.06
     Wohn
    0.06
    �
    0.06
    鄉
    0.06
     порядку
    0.06
     Centers
    0.06
     pilots
    0.06
    <Car
    0.06
    Loc
    0.06
     asylum
    0.06
    Activations Density 0.039%

    No Known Activations