© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78686
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to shader programming

    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
     PH
    -0.06
     deep
    -0.06
     Walnut
    -0.06
    ERP
    -0.06
     OH
    -0.06
     uncon
    -0.05
     Photos
    -0.05
     Sat
    -0.05
     unpl
    -0.05
     circum
    -0.05
    POSITIVE LOGITS
    .createFrom
    0.08
    .compile
    0.08
    ocode
    0.08
     INLINE
    0.08
    clide
    0.08
    CISION
    0.07
     Blockly
    0.07
    itage
    0.07
    ÙĨب
    0.07
    formace
    0.07
    Activations Density 0.057%

    No Known Activations