© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and interactions

    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
    apesh
    -0.07
    oca
    -0.07
    ucc
    -0.06
     dostup
    -0.06
    fid
    -0.06
    answered
    -0.06
    closure
    -0.06
    103
    -0.06
    ürger
    -0.06
    ect
    -0.06
    POSITIVE LOGITS
     recently
    0.28
    recent
    0.23
     recent
    0.21
     Recently
    0.21
    Recently
    0.20
     lately
    0.20
     yesterday
    0.17
    æľĢè¿ij
    0.16
    _recent
    0.15
     Recent
    0.13
    Activations Density 0.077%

    No Known Activations