© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4117
    Prev
    Next
    INDEX
    Explanations

    terms related to symbolic representation

    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
    iad
    -0.07
     Wonderland
    -0.07
    erview
    -0.07
    kö
    -0.07
    adem
    -0.06
    amar
    -0.06
    มà¸Ń
    -0.06
    amed
    -0.06
    orman
    -0.06
    forma
    -0.06
    POSITIVE LOGITS
    ically
    0.10
    -symbol
    0.09
     representing
    0.09
    represent
    0.09
    symbol
    0.08
     represent
    0.08
    .symbol
    0.07
    atically
    0.07
     of
    0.07
     represents
    0.07
    Activations Density 0.007%

    No Known Activations