© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 97446
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    instructions for roleplay that specify narrative perspective and roles, especially second-person directives and first‑person POV requirements.

    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_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
     BAŞ
    -0.06
     нанес
    -0.06
     rims
    -0.06
     FUNCT
    -0.06
     захоп
    -0.06
    .Ticks
    -0.06
    _MM
    -0.06
     onSubmit
    -0.06
    见
    -0.06
    茶
    -0.06
    POSITIVE LOGITS
     shame
    0.07
    Widget
    0.06
     своей
    0.06
    resolve
    0.06
     arrow
    0.06
    Genesis
    0.06
     своего
    0.06
    ROLL
    0.06
    phans
    0.06
    }
↵
↵
↵
    0.06
    Activations Density 0.103%

    No Known Activations