© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108923
    Prev
    Next
    INDEX
    Explanations

    Book reviews

    np_max-act · gemini-2.0-flash

    The neuron is detecting bits of blog‐post boilerplate and metadata—things like dates, section headings, tags (e.g. “meme,” “Subscribe,” “Pages”), and other structural/post‐template tokens.

    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
    Fred
    -0.07
     affiliation
    -0.07
     maintaining
    -0.06
     Kelvin
    -0.06
     geek
    -0.06
    Inform
    -0.06
     delta
    -0.06
    其他
    -0.06
    .getError
    -0.06
    _C
    -0.06
    POSITIVE LOGITS
    益
    0.07
     faç
    0.07
     Amnesty
    0.06
     lobbyists
    0.06
     σχ
    0.06
     SST
    0.06
    覧
    0.06
    ==-
    0.06
     exclus
    0.06
    _Public
    0.06
    Activations Density 0.019%

    No Known Activations