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. 15-RESID-POST-AA
    6. 41530
    Prev
    Next
    INDEX
    Explanations

    .type

    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
     땅
    -0.07
     indication
    -0.07
    �
    -0.07
     빛
    -0.07
     Table
    -0.06
     Takes
    -0.06
     Intersection
    -0.06
     �
    -0.06
     dressing
    -0.06
    기관
    -0.06
    POSITIVE LOGITS
    摘要
    0.06
     nad
    0.06
     Linux
    0.06
    >{{$
    0.06
    сед
    0.06
    ('\
    0.06
    .Builder
    0.06
     останов
    0.06
     Janeiro
    0.06
    真的
    0.06
    Activations Density 0.014%

    No Known Activations