© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34609
    Prev
    Next
    INDEX
    Explanations

    personalized or custom

    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
    ieber
    -0.09
    preneur
    -0.08
    angen
    -0.08
     pure
    -0.08
    arcer
    -0.08
     designed
    -0.08
     structured
    -0.08
     etiqu
    -0.08
    uster
    -0.08
    yles
    -0.08
    POSITIVE LOGITS
     individual
    0.38
     Individual
    0.33
    Custom
    0.31
     custom
    0.30
    custom
    0.29
     Custom
    0.29
    individual
    0.28
    Tail
    0.28
    Individual
    0.28
     individ
    0.27
    Activations Density 0.263%

    No Known Activations