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. 21712
    Prev
    Next
    INDEX
    Explanations

    preservation

    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
    Popup
    -0.08
     nikdo
    -0.07
     bite
    -0.07
     upt
    -0.07
     kicking
    -0.07
     Id
    -0.07
     stupidity
    -0.07
     Finder
    -0.07
     subtract
    -0.06
     dumb
    -0.06
    POSITIVE LOGITS
     preserved
    0.09
     conserv
    0.08
     Conserv
    0.07
     preserves
    0.07
    保
    0.07
     conservation
    0.07
    原
    0.07
     preservation
    0.07
     preserve
    0.07
     gift
    0.07
    Activations Density 0.020%

    No Known Activations