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. 93781
    Prev
    Next
    INDEX
    Explanations

    brew

    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
     Informationen
    -0.07
     wrist
    -0.06
    VECTOR
    -0.06
     Chaos
    -0.06
     sturdy
    -0.06
    工业
    -0.06
    _sync
    -0.06
     revoke
    -0.06
     projection
    -0.06
    ament
    -0.06
    POSITIVE LOGITS
    brew
    0.08
    EOF
    0.07
    recipes
    0.07
    отреб
    0.06
     개
    0.06
     карти
    0.06
    PCI
    0.06
     SSL
    0.06
    RS
    0.06
     sä
    0.06
    Activations Density 0.001%

    No Known Activations