© 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. 11887
    Prev
    Next
    INDEX
    Explanations

    completely dissimilar or irrelevant

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases making definitive statements or classifications about what something is or is not.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    isd
    -0.10
     dign
    -0.10
    Unnamed
    -0.09
    Impossible
    -0.09
     indiv
    -0.09
     identical
    -0.09
     entr
    -0.09
     unconventional
    -0.09
    quent
    -0.09
    upo
    -0.08
    POSITIVE LOGITS
     unrelated
    0.45
     completely
    0.33
    å®Įåħ¨
    0.26
     totally
    0.26
     irrelevant
    0.25
     Completely
    0.25
     completamente
    0.23
     tang
    0.22
     nothing
    0.21
     entirely
    0.21
    Activations Density 0.170%

    No Known Activations