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. 21327
    Prev
    Next
    INDEX
    Explanations

    I help we

    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
    반
    -0.07
     viral
    -0.06
     muster
    -0.06
    ätz
    -0.06
     devant
    -0.06
    DEPTH
    -0.06
    ihn
    -0.06
     nanoparticles
    -0.06
     Dirk
    -0.05
    νοντας
    -0.05
    POSITIVE LOGITS
    Highest
    0.07
    Clipboard
    0.07
     Sever
    0.07
    caler
    0.06
    .success
    0.06
    shi
    0.06
    .sdk
    0.06
    основ
    0.06
    GPS
    0.06
    (K
    0.06
    Activations Density 0.011%

    No Known Activations