Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109885
    Prev
    Next
    INDEX
    Explanations

    little

    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
    986
    -0.08
     seven
    -0.07
     Women
    -0.07
    /the
    -0.07
     one
    -0.06
    istant
    -0.06
    ậy
    -0.06
    privacy
    -0.06
     timed
    -0.06
    Good
    -0.06
    POSITIVE LOGITS
     little
    0.09
     bij
    0.07
    .centerY
    0.07
     tiny
    0.07
     малыш
    0.06
    	Logger
    0.06
    )',
    0.06
    ichern
    0.06
     td
    0.06
    _emlrt
    0.06
    Activations Density 0.088%

    No Known Activations