© 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. 14845
    Prev
    Next
    INDEX
    Explanations

    candidate outcomes assessment

    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
     Winn
    -0.09
    ebi
    -0.09
     lav
    -0.09
    aby
    -0.09
    _kw
    -0.09
     ARR
    -0.09
     Rocket
    -0.09
     sprint
    -0.08
     Crash
    -0.08
    lav
    -0.08
    POSITIVE LOGITS
     skill
    0.13
     Skill
    0.13
    ISCO
    0.12
     compet
    0.11
    skill
    0.11
     entr
    0.11
    Descriptors
    0.11
     job
    0.11
     Descriptor
    0.11
     Bloom
    0.11
    Activations Density 0.062%

    No Known Activations