Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65141
    Prev
    Next
    INDEX
    Explanations

    users use the

    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
    661
    -0.08
     parade
    -0.08
    atu
    -0.08
    008
    -0.08
    xE
    -0.08
    aturing
    -0.08
    .predicate
    -0.08
     Compatibility
    -0.07
     consolidation
    -0.07
     verbal
    -0.07
    POSITIVE LOGITS
     tone
    0.12
     spell
    0.11
     ton
    0.11
     sarc
    0.11
     ty
    0.10
     ell
    0.10
     physically
    0.10
     Tone
    0.10
    Idle
    0.09
    idle
    0.09
    Activations Density 0.134%

    No Known Activations