© 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 (Instruct)
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 110145
    Prev
    Next
    INDEX
    Explanations

    name

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    辆
    -0.07
    евые
    -0.06
    archs
    -0.06
     reason
    -0.06
     книги
    -0.06
    !;↵
    -0.06
     Modules
    -0.06
     dil
    -0.06
    ='".
    -0.06
    过程
    -0.06
    POSITIVE LOGITS
    ANEL
    0.07
     Bols
    0.07
    erdem
    0.07
     rede
    0.07
    encode
    0.07
     choosing
    0.07
    ertino
    0.07
    arov
    0.06
     Alternate
    0.06
    bane
    0.06
    Activations Density 0.000%

    No Known Activations