© 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. 87844
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and related symbols in text

    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
     (
    -0.06
     E
    -0.06
     Mal
    -0.06
    verse
    -0.06
    ila
    -0.06
     v
    -0.06
    ami
    -0.05
     van
    -0.05
     
    -0.05
     g
    -0.05
    POSITIVE LOGITS
    GuidId
    0.10
     destinationViewController
    0.08
    malink
    0.08
    QUIRE
    0.07
     TextAlign
    0.07
    572
    0.07
     tane
    0.07
    htags
    0.07
    htag
    0.07
    ccoli
    0.07
    Activations Density 0.302%

    No Known Activations