© 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. 44394
    Prev
    Next
    INDEX
    Explanations

    to fill, to be worth, it would

    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
    lbrace
    -0.10
     dod
    -0.09
     Hod
    -0.09
     unchanged
    -0.08
    ToInt
    -0.08
     dodge
    -0.08
    415
    -0.08
    ummies
    -0.08
    xad
    -0.08
     Gym
    -0.08
    POSITIVE LOGITS
     alternative
    0.34
     alternatives
    0.33
     competitor
    0.32
     rival
    0.32
     competing
    0.31
     compete
    0.31
     competition
    0.31
     competitors
    0.30
    alternative
    0.28
     rivalry
    0.28
    Activations Density 0.172%

    No Known Activations