© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30315
    Prev
    Next
    INDEX
    Explanations

    other and another

    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
    jekt
    -0.08
    ifle
    -0.08
    ør
    -0.08
    ırak
    -0.07
    .metro
    -0.07
    .Îij
    -0.07
    .gb
    -0.07
    oca
    -0.07
    amam
    -0.07
    isini
    -0.07
    POSITIVE LOGITS
     other
    0.43
     Other
    0.31
    åħ¶ä»ĸ
    0.30
    other
    0.29
    Other
    0.29
     andere
    0.28
     autres
    0.28
     OTHER
    0.27
     altri
    0.26
    -other
    0.26
    Activations Density 0.040%

    No Known Activations