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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 986
    Prev
    Next
    INDEX
    Explanations

    tickle and tickling

    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
     bleeding
    -0.12
     ram
    -0.11
     intimid
    -0.10
    åĨ²
    -0.09
     jaws
    -0.09
    isphere
    -0.09
     studs
    -0.09
     skulls
    -0.09
     fist
    -0.09
     fists
    -0.09
    POSITIVE LOGITS
     tick
    0.46
     Tick
    0.34
    tick
    0.30
    Tick
    0.30
    .tick
    0.22
     TICK
    0.21
     ticks
    0.20
    _tick
    0.20
    _Tick
    0.16
     ticking
    0.15
    Activations Density 0.057%

    No Known Activations