Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76014
    Prev
    Next
    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash

    stage directions or inline action cues in scripts/dialogues, especially those enclosed in brackets or parentheses

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    aklı
    -0.08
    yi
    -0.07
    .li
    -0.07
     it
    -0.07
    ským
    -0.06
    빙
    -0.06
    interfaces
    -0.06
    eniz
    -0.06
    ye
    -0.06
     jsem
    -0.06
    POSITIVE LOGITS
     Fact
    0.06
     risky
    0.06
     Rough
    0.06
    、小
    0.06
     déjà
    0.06
    阻
    0.06
    	scale
    0.06
    战争
    0.06
     ingr
    0.06
    .createNew
    0.06
    Activations Density 0.526%

    No Known Activations