© 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. 90901
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    The neuron activates on IUPAC-style chemical nomenclature fragments (e.g. “-idene,” “oxothiazolidin-3-yl,” “benzohydrazide”), i.e. technical substrings in systematic compound names.

    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
     ordeal
    -0.06
     θεω
    -0.06
    cház
    -0.06
     OL
    -0.06
     obliv
    -0.06
     pocket
    -0.06
    neighbor
    -0.06
     Volvo
    -0.06
    Mix
    -0.06
    clip
    -0.06
    POSITIVE LOGITS
    syntax
    0.07
    725
    0.07
    ้าม
    0.07
    _/
    0.06
    ?>>
    0.06
    0.06
    :],
    0.06
     rentals
    0.06
     Invitation
    0.06
    นว
    0.06
    Activations Density 0.036%

    No Known Activations