© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7872
    Prev
    Next
    INDEX
    Explanations

    blog comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     textbook
    -0.08
    Various
    -0.07
    questions
    -0.07
     Hint
    -0.07
     columnist
    -0.07
    ढ़
    -0.07
     Charity
    -0.06
     judged
    -0.06
     �
    -0.06
    =result
    -0.06
    POSITIVE LOGITS
    <Object
    0.07
     padre
    0.06
     productos
    0.06
    UserDefaults
    0.06
    Transition
    0.06
    rito
    0.06
    vote
    0.06
    .Bunifu
    0.06
    折
    0.06
     lia
    0.06
    Activations Density 0.012%

    No Known Activations