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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57518
    Prev
    Next
    INDEX
    Explanations

    internet articles

    np_max-act · gemini-2.0-flash

    This neuron activates on casual quoted dismissal phrases in reviews—e.g. seeing “Skip it” wrapped in quotation marks.

    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
    /List
    -0.08
    '),↵
    -0.07
    -->↵↵
    -0.07
    )↵↵↵↵
    -0.07
     "/");↵
    -0.06
    .movie
    -0.06
    .Space
    -0.06
    >"
↵
    -0.06
    ))),↵
    -0.06
     Hotels
    -0.06
    POSITIVE LOGITS
     YAML
    0.07
    .semantic
    0.06
     në
    0.06
     вп
    0.06
    alus
    0.06
    672
    0.06
     mayoría
    0.06
     sar
    0.06
     :::
    0.06
    .Documents
    0.06
    Activations Density 0.077%

    No Known Activations