© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 76584
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and parameters

    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
    anax
    -0.07
    erce
    -0.06
    croft
    -0.06
    egt
    -0.06
    IRD
    -0.06
     reducer
    -0.06
     Afr
    -0.06
    äter
    -0.06
     Fah
    -0.06
    eyJ
    -0.06
    POSITIVE LOGITS
     اÙĦتÙĪ
    0.06
     im
    0.06
     Nielsen
    0.06
     htt
    0.06
    èĪ¬
    0.06
     Cab
    0.06
    _armor
    0.06
    avor
    0.06
    616
    0.06
     éļ
    0.06
    Activations Density 0.079%

    No Known Activations