© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126794
    Prev
    Next
    INDEX
    Explanations

    Story progression

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on words and short phrases that mark plot or temporal progression (e.g. “then,” “eventually,” “find,” “over the course of…”).

    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
     mys
    -0.06
    andles
    -0.06
     overriding
    -0.06
     powdered
    -0.06
    呆
    -0.06
    .plugins
    -0.06
    алу
    -0.06
     rdr
    -0.06
     underage
    -0.06
    顔
    -0.06
    POSITIVE LOGITS
    提高
    0.07
     klik
    0.07
    Seleccion
    0.06
    fav
    0.06
    正确
    0.06
    (sel
    0.06
    Genre
    0.06
     mt
    0.06
     SIG
    0.06
    (_
    0.06
    Activations Density 0.071%

    No Known Activations