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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40788
    Prev
    Next
    INDEX
    Explanations

    references to historical events and notable figures

    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
     leather
    -0.06
    errer
    -0.06
    essian
    -0.06
     vel
    -0.06
     Vel
    -0.06
     Oil
    -0.06
     necessary
    -0.06
    anga
    -0.06
     Offline
    -0.06
    æ²¹
    -0.06
    POSITIVE LOGITS
     glass
    0.18
     Glass
    0.16
    glass
    0.15
    Glass
    0.15
    glas
    0.12
    çİ»çĴĥ
    0.12
     glasses
    0.12
     Glasses
    0.09
    Crystal
    0.09
     Glas
    0.09
    Activations Density 0.019%

    No Known Activations