© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128844
    Prev
    Next
    INDEX
    Explanations

    sexual content

    np_max-act · gemini-2.0-flash

    The neuron flags words that describe dark, sinful, decadent, or depraved erotic and carnal themes.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    小姐
    -0.07
    avicon
    -0.07
    otch
    -0.06
     home
    -0.06
    ungalow
    -0.06
     dzi
    -0.06
     子
    -0.06
     cosa
    -0.06
    acyj
    -0.06
     histogram
    -0.06
    POSITIVE LOGITS
    μιο
    0.07
    EXTERN
    0.07
    veal
    0.06
     sal
    0.06
    _APP
    0.06
    Cho
    0.06
    _bloc
    0.06
    into
    0.06
    �
    0.06
    .visibility
    0.06
    Activations Density 0.025%

    No Known Activations