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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40621
    Prev
    Next
    INDEX
    Explanations

    appeal

    np_max-act · gemini-2.0-flash

    The neuron detects the procedural heading that begins “On Appeal …” in court‐opinion or order documents.

    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
    airs
    -0.07
     textarea
    -0.06
    CON
    -0.06
    _player
    -0.06
     Cluster
    -0.06
    ataset
    -0.06
     Pixels
    -0.06
    add
    -0.06
     circles
    -0.06
     Fluid
    -0.06
    POSITIVE LOGITS
    ={}↵
    0.08
     corre
    0.08
     POSIX
    0.07
     SKU
    0.07
     MÜ
    0.07
     oč
    0.06
     OMAP
    0.06
    .ReadToEnd
    0.06
    -mark
    0.06
     Unsupported
    0.06
    Activations Density 0.001%

    No Known Activations