© 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. 43384
    Prev
    Next
    INDEX
    Explanations

    Podcast reviews

    np_max-act · gemini-2.0-flash

    The neuron spotlights “call-to-action” phrases—things like “subscribe,” “rate,” “follow us on iTunes/Stitcher/SoundCloud,” and similar promo or engagement prompts.

    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
     pt
    -0.07
    .card
    -0.07
     Spread
    -0.06
     PC
    -0.06
    EW
    -0.06
    V
    -0.06
    ANN
    -0.06
    .getC
    -0.06
    IV
    -0.06
     Carn
    -0.06
    POSITIVE LOGITS
    .optString
    0.06
    pub
    0.06
    _mov
    0.06
     bravery
    0.06
     crisis
    0.06
    ]=$
    0.06
    __',
    0.06
    占
    0.06
    aters
    0.06
    illus
    0.06
    Activations Density 0.018%

    No Known Activations