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. 27-RESID-POST-AA
    6. 73180
    Prev
    Next
    INDEX
    Explanations

    limb

    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
     etraf
    -0.06
     assignments
    -0.06
    .jar
    -0.06
    应当
    -0.06
     تو
    -0.06
     rd
    -0.06
     ""↵↵
    -0.06
     berlin
    -0.06
     daň
    -0.06
    display
    -0.06
    POSITIVE LOGITS
     limb
    0.08
    inine
    0.07
    imb
    0.07
    imedia
    0.07
    inen
    0.07
    IPP
    0.07
    ime
    0.07
     lime
    0.07
    翼
    0.07
    иль
    0.07
    Activations Density 0.006%

    No Known Activations