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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 46776
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    instructions prompting role-play or persona adoption, including directives to imitate a specific character, voice, tone, or style and to stay in character.

    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
     світі
    -0.07
     соответствии
    -0.06
    CORD
    -0.06
    摘
    -0.06
    IDE
    -0.06
     정부
    -0.06
     enfer
    -0.06
    ’nda
    -0.06
    (Operation
    -0.06
     generosity
    -0.06
    POSITIVE LOGITS
    .Features
    0.07
     Kag
    0.06
     Psych
    0.06
     viruses
    0.06
     Planned
    0.06
    ronym
    0.06
    (',',$
    0.06
    /*/
    0.06
     Pierce
    0.06
     colle
    0.06
    Activations Density 0.115%

    No Known Activations