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. 80981
    Prev
    Next
    INDEX
    Explanations

    it

    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
    780
    -0.08
     ballo
    -0.08
     určitě
    -0.07
    _pattern
    -0.07
    	cancel
    -0.07
     쉽
    -0.06
    ron
    -0.06
    围
    -0.06
     Especially
    -0.06
     surroundings
    -0.06
    POSITIVE LOGITS
    agrams
    0.07
    velle
    0.06
     předpis
    0.06
     vents
    0.06
    วม
    0.06
    nz
    0.06
    mez
    0.06
    .smart
    0.06
    KindOfClass
    0.05
     вироб
    0.05
    Activations Density 0.000%

    No Known Activations