© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10605
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions

    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
    Negative Logits
     Cald
    -0.10
    )throws
    -0.09
    rist
    -0.09
    ):?>\n
    -0.09
    taxonomy
    -0.09
    ainment
    -0.09
    berger
    -0.08
    atorio
    -0.08
     dozen
    -0.08
    abler
    -0.08
    POSITIVE LOGITS
    fare
    0.13
     yet
    0.12
     understanding
    0.12
    -y
    0.12
     approach
    0.11
     coverage
    0.11
     manner
    0.10
    /ext
    0.10
     suite
    0.10
    zza
    0.10
    Activations Density 0.028%

    No Known Activations