© 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. 11-RESID-POST-AA
    11. 49835
    Prev
    Next
    INDEX
    Explanations

    Programming

    np_max-act · gemini-2.0-flash

    entities related to governance and political situations.

    oai_token-act-pair · gpt-4o-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
    uben
    -0.08
    ugen
    -0.06
    Fault
    -0.06
    (rule
    -0.06
     jsonObj
    -0.06
    iliary
    -0.06
    Safety
    -0.06
    بح
    -0.06
    nob
    -0.06
    Proj
    -0.06
    POSITIVE LOGITS
     Construct
    0.07
     racket
    0.07
    ників
    0.06
     khổ
    0.06
     تل
    0.06
    -carousel
    0.06
    _dns
    0.06
    bones
    0.06
     Parents
    0.06
     masa
    0.06
    Activations Density 0.000%

    No Known Activations