© 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. 77552
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to room features and settings

    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
    eniable
    -0.07
    prung
    -0.07
     Ekon
    -0.07
    кÑĥÑģ
    -0.07
    GGLE
    -0.07
    Ãłm
    -0.07
     YÃĸ
    -0.07
    uppy
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    ãĤĴéĸĭ
    -0.07
    POSITIVE LOGITS
    s
    0.08
    avanaugh
    0.07
    933
    0.06
    ond
    0.06
    avr
    0.06
    amu
    0.06
    AB
    0.05
    -strokes
    0.05
    acey
    0.05
     Canary
    0.05
    Activations Density 0.011%

    No Known Activations