© 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. 60866
    Prev
    Next
    INDEX
    Explanations

    technical specifications or resource limits in computer system 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
    .scalablytyped
    -0.07
    ÑĢиÑĩ
    -0.07
    onz
    -0.07
    acades
    -0.06
    TimeInterval
    -0.06
    orney
    -0.06
    ücken
    -0.06
    å¹¹ç·ļ
    -0.06
    orca
    -0.06
    casecmp
    -0.06
    POSITIVE LOGITS
     memory
    0.13
     Memory
    0.11
    Memory
    0.11
    memory
    0.10
     RAM
    0.10
     MEMORY
    0.09
    RAM
    0.09
    _memory
    0.09
    (memory
    0.09
     Mem
    0.09
    Activations Density 0.028%

    No Known Activations