© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 84542
    Prev
    Next
    INDEX
    Explanations

    to

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ейн
    -0.07
     Contractor
    -0.06
    اب
    -0.06
    oi
    -0.06
    祭
    -0.06
    젝트
    -0.06
    USTER
    -0.06
    赫
    -0.06
    oki
    -0.06
    certificate
    -0.06
    POSITIVE LOGITS
    -prepend
    0.07
    顔を
    0.07
    .do
    0.07
     repeatedly
    0.07
    .isTrue
    0.06
     мере
    0.06
    品牌
    0.06
     dataSize
    0.06
     이루
    0.06
    (nd
    0.06
    Activations Density 0.092%

    No Known Activations