© 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. 42867
    Prev
    Next
    INDEX
    Explanations

    waste of time, lacks effectiveness

    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
    shal
    -0.10
     Saf
    -0.10
    chan
    -0.09
    $MESS
    -0.09
    _sensitive
    -0.09
     Regional
    -0.09
    pls
    -0.09
     Parm
    -0.09
    legg
    -0.09
     Remed
    -0.09
    POSITIVE LOGITS
     effectiveness
    0.15
     ultimately
    0.14
    ult
    0.13
     efficacy
    0.12
     instead
    0.12
     eventually
    0.12
     actually
    0.12
     Temporary
    0.12
     risks
    0.11
     dub
    0.11
    Activations Density 0.078%

    No Known Activations