© 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. 15-RESID-POST-AA
    11. 52096
    Prev
    Next
    INDEX
    Explanations

    curious

    np_max-act · gemini-2.0-flash

    text that is sexual or erotic in nature (including explicit requests and taboo/underage/consensual sexual scenarios).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     предпри
    -0.07
    _energy
    -0.07
    .sess
    -0.07
     mpl
    -0.07
     отношения
    -0.06
     Banco
    -0.06
    Cli
    -0.06
     rég
    -0.06
     economical
    -0.06
    .spin
    -0.06
    POSITIVE LOGITS
     curiosity
    0.09
     hearing
    0.07
    怀
    0.06
     libido
    0.06
     Таким
    0.06
     Unused
    0.06
    aud
    0.06
     curious
    0.06
    \",\
    0.06
     Customs
    0.06
    Activations Density 0.014%

    No Known Activations