© 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. 26821
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations in formal writing

    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
    ze
    -0.06
    oui
    -0.06
    achi
    -0.06
    erson
    -0.06
     dl
    -0.05
    ãĤĵãģ©
    -0.05
     disease
    -0.05
    ersen
    -0.05
     somehow
    -0.05
    Ñħ
    -0.05
    POSITIVE LOGITS
    frauen
    0.07
    izzard
    0.07
    chyb
    0.07
    yme
    0.07
    Looper
    0.07
    imity
    0.07
    abal
    0.07
    çĭ¼
    0.07
    ipping
    0.07
    rimp
    0.06
    Activations Density 0.081%

    No Known Activations