© 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. 15-LLAMASCOPE-RES-131K
    11. 27418
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to experiences and actions

    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
    éĻµ
    -0.07
    241
    -0.06
    uya
    -0.06
    ento
    -0.06
     Ñıв
    -0.06
    ystone
    -0.06
    caffold
    -0.06
     пока
    -0.06
    nable
    -0.06
    emade
    -0.06
    POSITIVE LOGITS
    нимаеÑĤ
    0.06
    acon
    0.06
     Marketable
    0.06
    ipp
    0.06
    NgModule
    0.06
    acl
    0.06
    ogie
    0.06
    æł·åŃIJ
    0.06
    İ
    0.06
     again
    0.06
    Activations Density 0.025%

    No Known Activations