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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43513
    Prev
    Next
    INDEX
    Explanations

    human-like

    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
    igkeit
    -0.12
    ereo
    -0.10
    ROKE
    -0.09
    flix
    -0.09
    á»ģ
    -0.08
    Phrase
    -0.08
     humanity
    -0.08
    çľī
    -0.08
    ropa
    -0.08
     uten
    -0.08
    POSITIVE LOGITS
    like
    0.27
    -like
    0.25
     like
    0.17
    _like
    0.16
    istic
    0.16
    LIKE
    0.15
    Like
    0.14
     Like
    0.13
     style
    0.13
    oids
    0.13
    Activations Density 0.017%

    No Known Activations