© 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. 16698
    Prev
    Next
    INDEX
    Explanations

    elements related to data management and retrieval in programming contexts

    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
    _OC
    -0.07
    nict
    -0.06
    èĥ
    -0.06
    okers
    -0.06
    EFA
    -0.06
     FactoryBot
    -0.06
    çŀ
    -0.06
    UGHT
    -0.06
    /XMLSchema
    -0.06
    trl
    -0.06
    POSITIVE LOGITS
     stored
    0.07
     store
    0.07
     storage
    0.07
    aul
    0.07
    store
    0.07
    stored
    0.07
     keys
    0.06
     record
    0.06
     key
    0.06
    ately
    0.06
    Activations Density 0.006%

    No Known Activations