Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84578
    Prev
    Next
    INDEX
    Explanations

    General descriptive text

    np_max-act · gemini-2.0-flash

    explicit descriptions of physical and sexual violence.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron specifically responds to graphic descriptions of sexual violence or assault.

    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
     Adler
    -0.07
     projectile
    -0.07
    .FIELD
    -0.07
     Sweat
    -0.07
    Owner
    -0.07
     exhibits
    -0.06
    .guild
    -0.06
    Direccion
    -0.06
    _SHADER
    -0.06
    Adresse
    -0.06
    POSITIVE LOGITS
     cic
    0.07
    friend
    0.07
    啦
    0.06
     arab
    0.06
    —"
    0.06
     everyday
    0.06
     occasions
    0.06
    —
    0.06
     schools
    0.06
    entar
    0.06
    Activations Density 0.004%

    No Known Activations