© 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. 15735
    Prev
    Next
    INDEX
    Explanations

    verbs indicating possibility or future action

    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
    ucc
    -0.08
    cmc
    -0.07
    /Area
    -0.07
     Kho
    -0.07
     Duffy
    -0.07
    NOW
    -0.06
    人ãģ¯
    -0.06
    âĻª
    -0.06
    ĶĶ
    -0.06
    tic
    -0.06
    POSITIVE LOGITS
    asmus
    0.07
    chedulers
    0.07
    que
    0.06
    ecal
    0.06
    lier
    0.06
    raquo
    0.06
    ummings
    0.06
    assa
    0.06
    chal
    0.06
    232
    0.06
    Activations Density 0.036%

    No Known Activations