Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65112
    Prev
    Next
    INDEX
    Explanations

    soil type

    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
    ******č\n
    -0.09
     BorderRadius
    -0.09
    creativecommons
    -0.09
    addError
    -0.09
    theValue
    -0.08
    å¹³æĪIJ
    -0.08
    fila
    -0.08
    .visualization
    -0.08
     Specs
    -0.08
     Downing
    -0.08
    POSITIVE LOGITS
     soil
    0.16
     type
    0.12
     types
    0.11
     Soil
    0.10
     Äijất
    0.09
     Licht
    0.09
    åľŁ
    0.09
     Rag
    0.09
     glitter
    0.09
     TYPE
    0.09
    Activations Density 0.014%

    No Known Activations