© 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. 14046
    Prev
    Next
    INDEX
    Explanations

    handle requests and situations

    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
    acades
    -0.10
     hob
    -0.10
     hog
    -0.09
    atore
    -0.09
    ICAST
    -0.09
    <?,
    -0.09
     Lies
    -0.09
    UMB
    -0.09
     hÆ°á»Łng
    -0.09
    ispens
    -0.08
    POSITIVE LOGITS
     situation
    0.18
     situations
    0.15
     affairs
    0.14
     Situation
    0.13
     cases
    0.12
     aspect
    0.12
     aftermath
    0.11
     ÑģиÑĤÑĥаÑĨии
    0.11
     tasks
    0.11
     delicate
    0.11
    Activations Density 0.045%

    No Known Activations