© 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. 79132
    Prev
    Next
    INDEX
    Explanations

    time-related information or references

    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
    oe
    -0.06
     Fridays
    -0.06
    ov
    -0.06
    justice
    -0.06
     Tyr
    -0.05
    å
    -0.05
    oft
    -0.05
     discrim
    -0.05
     flow
    -0.05
     Cummings
    -0.05
    POSITIVE LOGITS
     anale
    0.09
    aylight
    0.08
    UGE
    0.08
    orst
    0.07
    ullo
    0.07
    .sun
    0.07
    itud
    0.07
    pekt
    0.07
    ìĸ´ê°Ģ
    0.07
    heck
    0.07
    Activations Density 0.002%

    No Known Activations