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. 3-RESID-POST-AA
    6. 94796
    Prev
    Next
    INDEX
    Explanations

    мир

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gt
    -0.06
     undoubtedly
    -0.06
     rz
    -0.06
     POD
    -0.06
    (var
    -0.06
    udd
    -0.06
    허
    -0.06
     cabbage
    -0.06
     Grants
    -0.06
    ような
    -0.06
    POSITIVE LOGITS
     мире
    0.23
     мир
    0.17
     мира
    0.15
     миров
    0.08
     ми
    0.07
    ilmiştir
    0.07
    _CUSTOMER
    0.07
     ISA
    0.06
     عالم
    0.06
    [])
    0.06
    Activations Density 0.004%

    No Known Activations