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. 105680
    Prev
    Next
    INDEX
    Explanations

    code

    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
    440
    -0.06
     rept
    -0.06
     目
    -0.06
     Spor
    -0.06
     филь
    -0.06
     út
    -0.06
    昭
    -0.06
     свид
    -0.06
    migration
    -0.06
     absor
    -0.05
    POSITIVE LOGITS
     attend
    0.07
    when
    0.06
     IMPORTANT
    0.06
    _nth
    0.06
    цієн
    0.06
    -container
    0.06
    tesy
    0.06
    ."),↵
    0.06
    episode
    0.06
     apps
    0.06
    Activations Density 0.000%

    No Known Activations