© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    concepts related to bilingual education and language development

    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
    odo
    -0.07
    urator
    -0.06
    uges
    -0.06
    iffe
    -0.06
    ktop
    -0.06
     Banc
    -0.06
     asc
    -0.06
    stdcall
    -0.06
    cla
    -0.06
    osit
    -0.06
    POSITIVE LOGITS
     Hemisphere
    0.07
     hemisphere
    0.07
     processing
    0.07
     brain
    0.07
    @store
    0.06
    _FORE
    0.06
    ReadWrite
    0.06
    ineTransform
    0.06
     incon
    0.06
    HLT
    0.06
    Activations Density 0.005%

    No Known Activations