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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 110803
    Prev
    Next
    INDEX
    Explanations

    rivers forming borders

    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
    +=
    -0.07
    WebService
    -0.06
     sponge
    -0.06
    igmoid
    -0.06
    _TOP
    -0.06
    textarea
    -0.06
    εφ
    -0.06
    pickup
    -0.06
    mesini
    -0.06
     :,
    -0.06
    POSITIVE LOGITS
     Notices
    0.06
     कहत
    0.06
     Artists
    0.06
    _rand
    0.06
    _Header
    0.06
    ọ
    0.06
     runtime
    0.06
    ix
    0.06
     loggedIn
    0.06
     beneath
    0.06
    Activations Density 0.024%

    No Known Activations