© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32500
    Prev
    Next
    INDEX
    Explanations

    identificador único, nombre y puntero a un archivo de imagen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ»
    -0.12
     jpeg
    -0.11
     Blick
    -0.10
     pict
    -0.10
     Thumbnail
    -0.10
    çķ«
    -0.10
    .colors
    -0.10
    iar
    -0.09
     outputs
    -0.09
     JPEG
    -0.09
    POSITIVE LOGITS
     image
    0.15
    .ImageIcon
    0.14
    .imread
    0.14
    .load
    0.14
     asset
    0.14
     load
    0.14
     Load
    0.14
     URLRequest
    0.13
    asset
    0.12
     resource
    0.12
    Activations Density 0.057%

    No Known Activations