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. 11-RESID-POST-AA
    6. 104280
    Prev
    Next
    INDEX
    Explanations

    albums, music

    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_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
    treeview
    -0.07
    ยน
    -0.06
    390
    -0.06
    462
    -0.06
    _BUFF
    -0.06
    fits
    -0.06
    Plot
    -0.06
    Interpreter
    -0.06
    Chuck
    -0.06
     d
    -0.06
    POSITIVE LOGITS
    ophe
    0.07
     Relative
    0.06
     streamline
    0.06
    onyms
    0.06
    /down
    0.06
     horrible
    0.06
     op
    0.06
     Apr
    0.06
     vrij
    0.06
    ly
    0.06
    Activations Density 0.221%

    No Known Activations