© 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. 36943
    Prev
    Next
    INDEX
    Explanations

    question answer websites

    np_max-act · gemini-2.0-flash

    Text that looks like Q&A/forum interface metadata and labels (author/expert names, answer/answered/answerer tags, headings, timestamps and other UI elements).

    oai_token-act-pair · gpt-5-miniTriggered 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
    'all
    -0.07
    xa
    -0.07
    โก
    -0.06
    ে
    -0.06
    もし
    -0.06
     โ
    -0.06
    桌
    -0.06
    outers
    -0.06
     neph
    -0.06
    ’all
    -0.06
    POSITIVE LOGITS
    Chocolate
    0.07
    ději
    0.06
    _UNKNOWN
    0.06
     wilt
    0.06
    Listener
    0.06
    Symfony
    0.06
    -----------
↵
    0.06
    ContentType
    0.06
     Melee
    0.06
    TJ
    0.06
    Activations Density 0.022%

    No Known Activations