© 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. 38096
    Prev
    Next
    INDEX
    Explanations

    explanation and justification

    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
     Thr
    -0.09
    indle
    -0.09
    uelles
    -0.09
    igure
    -0.09
    annot
    -0.09
     Hob
    -0.09
    egment
    -0.08
    ESP
    -0.08
     Bracket
    -0.08
    altet
    -0.08
    POSITIVE LOGITS
     justification
    0.15
     justify
    0.15
     justified
    0.14
     reasons
    0.13
    çIJĨçĶ±
    0.13
     reasoning
    0.12
     then
    0.12
     followed
    0.12
     reason
    0.11
    reason
    0.11
    Activations Density 0.024%

    No Known Activations