Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 87021
    Prev
    Next
    INDEX
    Explanations

    speed

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inher
    -0.07
     الانت
    -0.07
     koji
    -0.07
    遺
    -0.07
    líb
    -0.07
     právní
    -0.07
     delicate
    -0.07
     rece
    -0.07
    lices
    -0.06
     Registrar
    -0.06
    POSITIVE LOGITS
     speed
    0.14
    speed
    0.12
     Speed
    0.12
    Speed
    0.11
    _Speed
    0.11
     SPEED
    0.11
     speeds
    0.10
    PEED
    0.10
    -speed
    0.10
     Speedway
    0.10
    Activations Density 0.016%

    No Known Activations