© 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. 85714
    Prev
    Next
    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on relative pronouns and subordinating conjunctions (e.g. “which,” “that”) that introduce explanatory or linking clauses.

    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
    ^{
    -0.06
     comunic
    -0.06
     Electron
    -0.06
     stepper
    -0.06
    _plan
    -0.06
    ас
    -0.06
    ,strong
    -0.06
    \DependencyInjection
    -0.06
     Lup
    -0.06
     Voc
    -0.06
    POSITIVE LOGITS
    nych
    0.07
    rotate
    0.07
    browser
    0.06
    ّم
    0.06
    £o
    0.06
    ound
    0.06
     lieutenant
    0.06
     sort
    0.06
     abi
    0.06
    creator
    0.06
    Activations Density 0.087%

    No Known Activations