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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5859
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on code-style keywords and tokens (e.g. SQL commands, JSON/JOLT operations, SPARQL clauses, programming annotations), i.e. it spots programming‐language or query‐language constructs.

    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
     "%"
    -0.07
     引
    -0.07
     `}↵
    -0.07
    (thing
    -0.07
    (".");↵
    -0.06
     CLL
    -0.06
    _major
    -0.06
     vis
    -0.06
    ----------------------------------------------------------------------
    -0.06
    _running
    -0.06
    POSITIVE LOGITS
     Wilderness
    0.08
     taraf
    0.07
    老师
    0.06
    Descriptions
    0.06
     pouze
    0.06
    _atual
    0.06
    奈
    0.06
    modation
    0.06
     станет
    0.06
     Yue
    0.06
    Activations Density 0.234%

    No Known Activations