© 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. 7-RESID-POST-AA
    11. 113225
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    double-quote characters marking the start of a JSON/string value.

    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_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
    пеки
    -0.06
    --------↵↵
    -0.06
     readability
    -0.06
     primeiro
    -0.06
     savvy
    -0.06
     gì
    -0.06
     hoạt
    -0.06
    ">

↵
    -0.06
     рам
    -0.06
     vực
    -0.06
    POSITIVE LOGITS
    iams
    0.08
     Zimbabwe
    0.07
     kicking
    0.06
    DN
    0.06
    LT
    0.06
    :"
    0.06
     Arb
    0.06
     वर
    0.06
     Pakistani
    0.06
     grop
    0.06
    Activations Density 0.001%

    No Known Activations