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. 19-RESID-POST-AA
    6. 31087
    Prev
    Next
    INDEX
    Explanations

    den

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     назива
    -0.07
     nhất
    -0.07
    Atlantic
    -0.06
     teas
    -0.06
    	lbl
    -0.06
    vk
    -0.06
    021
    -0.06
     movable
    -0.06
     tablesp
    -0.06
    037
    -0.06
    POSITIVE LOGITS
    ден
    0.09
    dden
    0.08
    den
    0.08
    yun
    0.07
    DON
    0.07
    _CODES
    0.07
    дал
    0.07
    REN
    0.07
    dens
    0.07
     accredited
    0.07
    Activations Density 0.014%

    No Known Activations