© 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. 13370
    Prev
    Next
    INDEX
    Explanations

    may followed by potential verbs

    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
     ever
    -0.09
    tright
    -0.08
    idi
    -0.08
    keh
    -0.08
    YLE
    -0.08
    beros
    -0.08
    онÑĮ
    -0.08
    intree
    -0.08
    acades
    -0.08
    spr
    -0.08
    POSITIVE LOGITS
    oral
    0.22
    onna
    0.21
    ารย
    0.20
    hem
    0.19
    ors
    0.18
    ily
    0.16
    -être
    0.16
    haps
    0.16
    hap
    0.14
    yyyy
    0.13
    Activations Density 0.056%

    No Known Activations