© 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. 84559
    Prev
    Next
    INDEX
    Explanations

    technical details related to image processing and graphical effects

    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
    LAG
    -0.07
    external
    -0.07
    _initializer
    -0.07
    obsolete
    -0.06
    illez
    -0.06
    売
    -0.06
     vyh
    -0.06
    μο
    -0.06
     Lag
    -0.06
     parody
    -0.06
    POSITIVE LOGITS
     transparency
    0.09
     effect
    0.07
     transparent
    0.07
     Transparency
    0.07
     layer
    0.07
     opacity
    0.07
     effects
    0.06
    opa
    0.06
    jab
    0.06
    .effect
    0.06
    Activations Density 0.009%

    No Known Activations