© 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. 83752
    Prev
    Next
    INDEX
    Explanations

    references to instances or cases of incidents or examples of situations

    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
    иÑģлов
    -0.07
     spar
    -0.06
    GV
    -0.06
     дÑĥÑĪ
    -0.06
    -Smith
    -0.06
     Mor
    -0.06
    coil
    -0.06
     здоб
    -0.06
    Ùħز
    -0.06
    uj
    -0.06
    POSITIVE LOGITS
     instances
    0.10
     cases
    0.09
    instances
    0.09
     Instances
    0.09
    Instances
    0.09
    Cases
    0.08
     Cases
    0.07
     of
    0.07
     case
    0.07
     instance
    0.07
    Activations Density 0.023%

    No Known Activations