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. 15-RESID-POST-AA
    6. 111020
    Prev
    Next
    INDEX
    Explanations

    hurricane names

    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
    044
    -0.07
    "Yeah
    -0.06
    "Well
    -0.06
    Wei
    -0.06
    	Player
    -0.06
    oted
    -0.06
    'email
    -0.06
    ятия
    -0.06
     fox
    -0.06
    (ed
    -0.06
    POSITIVE LOGITS
    etest
    0.07
     handwritten
    0.07
    Represent
    0.07
    -publish
    0.06
    ARP
    0.06
     Prospect
    0.06
    енз
    0.06
    XXXX
    0.06
    Topology
    0.06
    ωνα
    0.06
    Activations Density 0.004%

    No Known Activations