© 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
    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. 799
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of named historical battles (titles like “Battle of the … River”).

    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
    controls
    -0.07
     Scenes
    -0.07
    dfs
    -0.06
    _ts
    -0.06
     snapshot
    -0.06
    .Points
    -0.06
     BUF
    -0.06
     Syrian
    -0.06
     birth
    -0.06
     rainfall
    -0.06
    POSITIVE LOGITS
    _thumb
    0.07
    asyon
    0.06
    &r
    0.06
     stained
    0.06
     puta
    0.06
     underside
    0.06
     …
    0.06
    _browser
    0.06
    рование
    0.06
    вання
    0.06
    Activations Density 0.033%

    No Known Activations