© 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. 17-LLAMASCOPE-RES-131K
    11. 40845
    Prev
    Next
    INDEX
    Explanations

    numerical values and their context in various lists or descriptions

    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
    жд
    -0.07
    _FOREACH
    -0.07
    lander
    -0.07
    važ
    -0.06
     fır
    -0.06
    eyh
    -0.06
    oug
    -0.06
    epad
    -0.06
    нÑĮ
    -0.06
     zas
    -0.06
    POSITIVE LOGITS
    akis
    0.07
    byn
    0.06
    antz
    0.06
     Holt
    0.06
    643
    0.06
    152
    0.06
     Mega
    0.06
     TMPro
    0.06
     RequestMethod
    0.06
    284
    0.06
    Activations Density 0.003%

    No Known Activations