© 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. 36379
    Prev
    Next
    INDEX
    Explanations

    gra, graft, grav, graz

    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
    grim
    -0.11
    eut
    -0.11
    jsc
    -0.09
    adro
    -0.09
    istic
    -0.09
     Tham
    -0.09
     watt
    -0.09
    ares
    -0.09
    chts
    -0.09
    -hide
    -0.09
    POSITIVE LOGITS
    (Gravity
    0.15
    itational
    0.12
    fruit
    0.12
    roots
    0.12
    agra
    0.11
    à¥Ģण
    0.10
     ÐĵÑĢи
    0.10
    ffiti
    0.10
    ophone
    0.10
    èĢ³
    0.10
    Activations Density 0.024%

    No Known Activations