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. 12688
    Prev
    Next
    INDEX
    Explanations

    copy

    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
     north
    -0.07
     channel
    -0.07
     southeast
    -0.06
     east
    -0.06
     department
    -0.06
     бизнес
    -0.06
     webinar
    -0.06
    년에
    -0.06
    _EXPECT
    -0.06
     navigation
    -0.06
    POSITIVE LOGITS
     eapply
    0.07
     Trial
    0.07
     copies
    0.07
    .and
    0.06
     CALL
    0.06
     l
    0.06
     replicas
    0.06
     crossAxisAlignment
    0.06
     \:
    0.06
    照片
    0.06
    Activations Density 0.013%

    No Known Activations