© 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. 15-LLAMASCOPE-RES-131K
    11. 61648
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and notation related to definitions and proofs

    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
    essel
    -0.07
    bdb
    -0.06
    umas
    -0.06
    enthal
    -0.06
    YL
    -0.06
    ESCO
    -0.06
    oS
    -0.06
    ares
    -0.06
    fef
    -0.06
    pson
    -0.06
    POSITIVE LOGITS
    s
    0.08
    sus
    0.07
    srv
    0.07
    ogany
    0.07
    etc
    0.07
    squ
    0.07
    sil
    0.06
    sWith
    0.06
    scape
    0.06
    icator
    0.06
    Activations Density 0.026%

    No Known Activations