© 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. 13106
    Prev
    Next
    INDEX
    Explanations

    chemical processes

    np_max-act · gemini-2.0-flash

    This neuron activates on terms that introduce or describe specific steps in a chemical production procedure (e.g., “Step,” “hydrolysis,” “reaction,” “carried,” “treated”).

    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
    _full
    -0.07
     г
    -0.06
    _Server
    -0.06
     cuatro
    -0.06
    -tree
    -0.06
    (dtype
    -0.06
    _big
    -0.06
     AIM
    -0.06
     svn
    -0.06
     stratej
    -0.06
    POSITIVE LOGITS
    δης
    0.07
    ://%
    0.06
     모델
    0.06
    naire
    0.06
     στον
    0.06
     Assange
    0.06
    ophobia
    0.06
    okoj
    0.06
    -find
    0.06
    Interrupt
    0.06
    Activations Density 0.050%

    No Known Activations