© 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. 436
    Prev
    Next
    INDEX
    Explanations

    all followed by various words

    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
    ndx
    -0.09
    /loose
    -0.09
    xmm
    -0.09
    ucas
    -0.09
    _HT
    -0.09
     withObject
    -0.09
    lfw
    -0.09
    ï½Ĵ
    -0.08
    aten
    -0.08
    prite
    -0.08
    POSITIVE LOGITS
     kinds
    0.23
    uv
    0.22
     manner
    0.20
     major
    0.18
    uring
    0.17
     levels
    0.16
    usion
    0.16
     except
    0.16
    aying
    0.16
     kind
    0.15
    Activations Density 0.057%

    No Known Activations