© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42518
    Prev
    Next
    INDEX
    Explanations

    to be or to do

    np_max-act · gemini-2.0-flash

    The neuron selectively activates for occurrences of the verb “do” (including its inflected forms like “does,” “do,” and “done”).

    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
    Cluster
    -0.07
    PCI
    -0.07
    chat
    -0.07
    phia
    -0.06
    ,application
    -0.06
    RELEASE
    -0.06
    _topics
    -0.06
     [[
    -0.06
    Ré
    -0.06
    viders
    -0.06
    POSITIVE LOGITS
     Народ
    0.06
     Vs
    0.06
     tactic
    0.06
     Well
    0.06
    .getDocument
    0.06
     orgasm
    0.06
     dipped
    0.06
     �
    0.06
    .pm
    0.06
     meth
    0.06
    Activations Density 0.013%

    No Known Activations