© 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. 39687
    Prev
    Next
    INDEX
    Explanations

    specifications and performance attributes of mobile devices

    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
     Autodesk
    -0.07
     Subaru
    -0.07
    rud
    -0.06
    lect
    -0.06
    aminer
    -0.06
    svp
    -0.06
    çĶļ
    -0.06
     Cisco
    -0.06
    æľ
    -0.06
    XB
    -0.06
    POSITIVE LOGITS
     models
    0.08
     unlocked
    0.07
    osp
    0.07
    iland
    0.07
    izzo
    0.07
     اÙĦØ°
    0.07
     Models
    0.07
    ICS
    0.06
     model
    0.06
    actories
    0.06
    Activations Density 0.033%

    No Known Activations