© 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. 6524
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on standalone list‐item numbers (single digits) marking entries in a numbered list.

    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
    ối
    -0.07
    yaw
    -0.07
    unc
    -0.06
     Injection
    -0.06
     salts
    -0.06
     Judith
    -0.06
    inch
    -0.06
    -inc
    -0.06
     conservation
    -0.06
    umblr
    -0.06
    POSITIVE LOGITS
     aluno
    0.07
    apons
    0.07
     autour
    0.07
     togg
    0.07
    -cur
    0.07
    \Url
    0.07
    _buttons
    0.06
    Locations
    0.06
    Juan
    0.06
    (issue
    0.06
    Activations Density 0.030%

    No Known Activations