© 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. 83077
    Prev
    Next
    INDEX
    Explanations

    discussions about data storage and content archiving

    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
    gili
    -0.07
    æ´ŀ
    -0.07
    alytics
    -0.07
    OKIE
    -0.07
     åľŁ
    -0.07
    Dual
    -0.06
    blem
    -0.06
    heimer
    -0.06
     fins
    -0.06
    rsa
    -0.06
    POSITIVE LOGITS
     storage
    0.10
     preservation
    0.09
     Storage
    0.09
     preserving
    0.07
    .storage
    0.07
    -storage
    0.07
     Preservation
    0.07
     preserve
    0.07
    _storage
    0.07
     storing
    0.07
    Activations Density 0.005%

    No Known Activations