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

    Neuronpedia

    APICircuit 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. 111204
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    (sample
    -0.08
    decess
    -0.06
    ();}↵
    -0.06
     getters
    -0.06
    semble
    -0.06
     internals
    -0.06
     Ceramic
    -0.06
     fora
    -0.06
     потреб
    -0.06
     coherence
    -0.06
    POSITIVE LOGITS
     coment
    0.07
    (sess
    0.07
    (links
    0.06
    ać
    0.06
    nek
    0.06
    channel
    0.06
    �权
    0.06
     Kind
    0.06
    貸
    0.06
    Matthew
    0.06
    Activations Density 0.000%

    No Known Activations