© 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. 12095
    Prev
    Next
    INDEX
    Explanations

    bear hug, sensory, roll, wrap

    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
     cups
    -0.09
     bags
    -0.09
     sacks
    -0.09
    flip
    -0.09
    agle
    -0.09
    us
    -0.09
    Wallet
    -0.09
     envelopes
    -0.09
     pouch
    -0.09
     mushroom
    -0.09
    POSITIVE LOGITS
     roll
    0.23
     rolls
    0.22
    å·»
    0.21
    .roll
    0.20
    roll
    0.19
     Roll
    0.19
    rolls
    0.19
    ROLL
    0.18
     wrap
    0.18
     unw
    0.18
    Activations Density 0.061%

    No Known Activations