© 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. 71123
    Prev
    Next
    INDEX
    Explanations

    numeric values and associated metadata, likely in a data or image context

    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
    365
    -0.06
     mir
    -0.06
    PostBack
    -0.06
    Enlarge
    -0.06
     proport
    -0.06
    180
    -0.06
     pie
    -0.06
     Damon
    -0.05
    109
    -0.05
     Fay
    -0.05
    POSITIVE LOGITS
    chwitz
    0.07
     æ¤
    0.07
    INVAL
    0.07
    aban
    0.07
    leigh
    0.06
    COLUMN
    0.06
    edio
    0.06
    ollo
    0.06
    nict
    0.06
    SETS
    0.06
    Activations Density 0.004%

    No Known Activations