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. 15-RESID-POST-AA
    6. 54359
    Prev
    Next
    INDEX
    Explanations

    j

    np_max-act · gemini-2.0-flash
    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
     snad
    -0.07
    SEX
    -0.07
     bends
    -0.07
     зв
    -0.06
    .Lookup
    -0.06
     第二
    -0.06
    asionally
    -0.06
     aba
    -0.06
     enclosing
    -0.06
     kid
    -0.06
    POSITIVE LOGITS
     peas
    0.07
     Ting
    0.07
    _SEND
    0.07
     Dana
    0.06
    AuthToken
    0.06
     田
    0.06
    шин
    0.06
     音
    0.06
    vendor
    0.06
    mean
    0.06
    Activations Density 0.000%

    No Known Activations