© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3427
    Prev
    Next
    INDEX
    Explanations

    structural elements of mathematical documents, such as definitions, lemmas, and theorems

    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
    itura
    -0.09
    iggs
    -0.08
    apesh
    -0.07
    ütün
    -0.07
    oken
    -0.07
    IllegalAccessException
    -0.07
    ochen
    -0.07
    igen
    -0.07
    Ñīин
    -0.07
    icari
    -0.07
    POSITIVE LOGITS
    orts
    0.07
    .scalablytyped
    0.06
    TEX
    0.06
     Chan
    0.06
    unset
    0.06
    çł
    0.05
    erap
    0.05
     Brace
    0.05
    esa
    0.05
     weekly
    0.05
    Activations Density 0.008%

    No Known Activations