© 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. 38111
    Prev
    Next
    INDEX
    Explanations

    entailment, contradiction, follows, inferred

    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
    nze
    -0.10
     exotic
    -0.09
     âĹĦ
    -0.09
    gaard
    -0.09
    asts
    -0.09
    ê´Ģ리ìŀIJ
    -0.09
    interpreted
    -0.09
    akov
    -0.08
    ovich
    -0.08
    θÏħ
    -0.08
    POSITIVE LOGITS
     supported
    0.22
     Supported
    0.17
     consequence
    0.16
     ded
    0.16
    Supported
    0.16
    supported
    0.15
     consequences
    0.14
    -supported
    0.14
     follows
    0.14
    _supported
    0.14
    Activations Density 0.068%

    No Known Activations