© 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. 41532
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash

    This neuron detects the vertical-bar “|” delimiter when it’s used in headings or metadata lines (e.g. around dates, runtimes, edition/issue numbers, 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
    roads
    -0.07
    chos
    -0.07
    -zone
    -0.07
    ：<
    -0.07
    umed
    -0.07
    -app
    -0.06
    logy
    -0.06
     لر
    -0.06
    /test
    -0.06
    ,top
    -0.06
    POSITIVE LOGITS
     |
    0.14
    '|
    0.08
    |
    0.07
    ("|
    0.07
     сказала
    0.06
     "|
    0.06
     Triangle
    0.06
     devlet
    0.06
    .HorizontalAlignment
    0.06
    .yahoo
    0.06
    Activations Density 0.009%

    No Known Activations