Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 40472
    Prev
    Next
    INDEX
    Explanations

    ome

    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
     Width
    -0.07
    !),
    -0.07
    acity
    -0.07
     visibility
    -0.06
     Tuy
    -0.06
     programma
    -0.06
     alta
    -0.06
    ={[
    -0.06
     Fukushima
    -0.06
     других
    -0.06
    POSITIVE LOGITS
     become
    0.07
     generalized
    0.07
     sack
    0.06
     Toilet
    0.06
    .COMP
    0.06
    Coming
    0.06
    _EXTERN
    0.06
     предназнач
    0.06
    Oct
    0.06
    Ide
    0.06
    Activations Density 0.000%

    No Known Activations