© 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. 90160
    Prev
    Next
    INDEX
    Explanations

    formal disclaimers about information and legal restrictions

    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
     when
    -0.06
     کرÛĮ
    -0.06
    aise
    -0.06
    947
    -0.05
     perish
    -0.05
     Holt
    -0.05
    gne
    -0.05
    gars
    -0.05
    sted
    -0.05
     rms
    -0.05
    POSITIVE LOGITS
    Republic
    0.08
     виб
    0.08
    /li
    0.07
    ÑĤал
    0.07
    alama
    0.07
    ÌĨ
    0.07
    eton
    0.07
    angl
    0.07
    ucks
    0.07
    anager
    0.07
    Activations Density 0.003%

    No Known Activations