© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75050
    Prev
    Next
    INDEX
    Explanations

    self-reference

    np_max-act · gemini-2.0-flash

    mentions of self-reference or ownership (words like "itself", "own", "self-", indicating actions directed at the subject itself).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    _FMT
    -0.06
    Common
    -0.06
     Common
    -0.06
    Helper
    -0.06
    Seeing
    -0.06
    _output
    -0.06
    .*;↵↵
    -0.06
    -this
    -0.06
    Except
    -0.06
     Lambda
    -0.06
    POSITIVE LOGITS
    _enqueue
    0.08
     میزان
    0.07
     สร
    0.07
     провести
    0.06
     Boehner
    0.06
    bero
    0.06
    elenium
    0.06
     gebru
    0.06
     проблемы
    0.06
    .getApp
    0.06
    Activations Density 0.064%

    No Known Activations