Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1463
    Prev
    Next
    INDEX
    Explanations

    [](

    np_max-act · gemini-2.0-flash

    The neuron responds strongly to the “![](” token sequence, i.e. the start of a Markdown image‐embedding/link syntax.

    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
     holy
    -0.06
     Maven
    -0.06
    }↵↵↵
    -0.06
     Away
    -0.06
     sne
    -0.06
    DrawerToggle
    -0.06
    clicked
    -0.06
    lige
    -0.06
    )\
    -0.06
    .setText
    -0.06
    POSITIVE LOGITS
     угл
    0.07
    _PAD
    0.07
     boyunca
    0.07
    全面
    0.06
    495
    0.06
    overn
    0.06
    orestation
    0.06
    544
    0.06
    .phi
    0.06
    .webkit
    0.06
    Activations Density 0.001%

    No Known Activations