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. 7-RESID-POST-AA
    6. 128959
    Prev
    Next
    INDEX
    Explanations

    programming references and 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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IX
    -0.07
     آمریکا
    -0.07
    атку
    -0.07
     destruct
    -0.06
     negatives
    -0.06
     unfold
    -0.06
    -running
    -0.06
     adress
    -0.06
    Expert
    -0.06
    second
    -0.06
    POSITIVE LOGITS
     disclosed
    0.07
    .pix
    0.06
    direction
    0.06
     comparatively
    0.06
    plemented
    0.06
     прояв
    0.06
    .Σ
    0.05
     Classification
    0.05
    �
    0.05
     Goblin
    0.05
    Activations Density 0.044%

    No Known Activations