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. 80886
    Prev
    Next
    INDEX
    Explanations

    d

    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
     corros
    -0.07
     hill
    -0.07
     defect
    -0.07
    	container
    -0.07
     wider
    -0.07
     quer
    -0.07
    .back
    -0.07
     Burning
    -0.07
     answer
    -0.07
    ocker
    -0.07
    POSITIVE LOGITS
    Es
    0.06
     may
    0.06
    ((&___
    0.06
    raits
    0.06
    験
    0.06
    ージ
    0.06
    indexed
    0.06
     بأ
    0.06
    Em
    0.06
    ımızın
    0.06
    Activations Density 0.004%

    No Known Activations