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. 15-RESID-POST-AA
    6. 12676
    Prev
    Next
    INDEX
    Explanations

    TR

    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
    มาก
    -0.07
     запис
    -0.06
    igsaw
    -0.06
     Gim
    -0.06
    Tank
    -0.06
     emerg
    -0.06
    _btn
    -0.06
     Parish
    -0.06
     divorce
    -0.06
    자의
    -0.06
    POSITIVE LOGITS
    =True
    0.08
    ':['
    0.07
     opinion
    0.07
    чен
    0.07
     Quote
    0.06
     algun
    0.06
    include
    0.06
     spies
    0.06
     clearly
    0.06
    clear
    0.06
    Activations Density 0.002%

    No Known Activations