© 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. 30044
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron detects meta-discourse signposts indicating that the text is giving an overview or summary (e.g. words like “review,” “summarize,” “current,” “recent,” “highlight,” etc.).

    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
    -css
    -0.07
    ssc
    -0.07
     |=
    -0.07
    <Test
    -0.07
    .Color
    -0.06
     NTN
    -0.06
    .From
    -0.06
    _BUTTON
    -0.06
    dsa
    -0.06
     observer
    -0.06
    POSITIVE LOGITS
     berg
    0.07
    =device
    0.06
    lacağı
    0.06
     Slug
    0.06
     meteor
    0.06
    ーボ
    0.06
     FLAC
    0.06
    ॉय
    0.06
     pertinent
    0.06
     ре
    0.06
    Activations Density 0.051%

    No Known Activations