© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44447
    Prev
    Next
    INDEX
    Explanations

    file transfer and examples

    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
     Redistributions
    -0.09
    .MixedReality
    -0.08
    iali
    -0.08
    ranÃŃ
    -0.08
    endcode
    -0.08
    -lfs
    -0.07
    _TypeInfo
    -0.07
    inspace
    -0.07
    ÙĪÙĦÙĬÙĪ
    -0.07
    ıb
    -0.07
    POSITIVE LOGITS
    hem
    0.08
    lashes
    0.08
     seper
    0.07
    acro
    0.07
    :uint
    0.07
    gars
    0.07
     ústav
    0.07
    fir
    0.07
    toISOString
    0.07
    .pb
    0.07
    Activations Density 0.265%

    No Known Activations