© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 70653
    Prev
    Next
    INDEX
    Explanations

    Online

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seats
    -0.07
     Hud
    -0.07
     disparate
    -0.07
    amat
    -0.07
     stup
    -0.07
    Stat
    -0.07
     repost
    -0.06
     pm
    -0.06
    keep
    -0.06
     seat
    -0.06
    POSITIVE LOGITS
     online
    0.21
     Online
    0.18
    online
    0.13
    Online
    0.13
     ONLINE
    0.11
    _online
    0.09
     offline
    0.09
    .online
    0.08
    _WORLD
    0.08
    在线
    0.08
    Activations Density 0.018%

    No Known Activations