© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 125746
    Prev
    Next
    INDEX
    Explanations

    "Nothing" as a response

    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
    ,rp
    -0.07
     sum
    -0.06
    GeneratedValue
    -0.06
     indefinitely
    -0.06
     někdo
    -0.06
     RESULT
    -0.06
     herpes
    -0.06
     KP
    -0.06
    자동
    -0.06
     ct
    -0.06
    POSITIVE LOGITS
     robust
    0.06
     studies
    0.06
     logic
    0.06
    Strong
    0.06
    ánd
    0.06
    ENDING
    0.06
     xác
    0.06
    esinde
    0.06
    ưu
    0.06
    pun
    0.06
    Activations Density 0.006%

    No Known Activations