© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79214
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to programming and API functionalities

    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
    ault
    -0.08
    ittel
    -0.07
    auer
    -0.06
    onation
    -0.06
    ież
    -0.06
    leur
    -0.06
    arlo
    -0.06
    uyu
    -0.06
    uco
    -0.06
    ilit
    -0.06
    POSITIVE LOGITS
    panic
    0.08
    ENTA
    0.07
    ÑĪÑĸ
    0.07
    ÑĢай
    0.07
    ANJI
    0.07
     LRV
    0.06
    .scalablytyped
    0.06
    ÑĢÑĥн
    0.06
    graded
    0.06
    _AX
    0.06
    Activations Density 0.006%

    No Known Activations