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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40527
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts, particularly in graph theory and related fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âh
    -0.07
    isses
    -0.06
    uco
    -0.06
    byn
    -0.06
     kâ
    -0.06
    ôm
    -0.06
    Ñģим
    -0.06
    ensi
    -0.06
    ede
    -0.06
    erde
    -0.06
    POSITIVE LOGITS
    199
    0.08
    198
    0.07
    201
    0.07
    196
    0.07
    ục
    0.07
    croft
    0.07
    AUSE
    0.06
    USTER
    0.06
    .LookAndFeel
    0.06
    MeasureSpec
    0.06
    Activations Density 0.016%

    No Known Activations