© 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. 41291
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or positive experiences

    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
    ina
    -0.07
    dy
    -0.07
    here
    -0.06
    _RENDERER
    -0.06
    owing
    -0.06
    нÑĮ
    -0.06
     Lew
    -0.06
    owed
    -0.06
    IQUE
    -0.06
    /from
    -0.06
    POSITIVE LOGITS
     hearing
    0.09
    ably
    0.09
     seeing
    0.08
    (ed
    0.07
     frequent
    0.07
    nest
    0.07
     being
    0.06
     having
    0.06
     thrill
    0.06
    741
    0.06
    Activations Density 0.012%

    No Known Activations