© 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. 70975
    Prev
    Next
    INDEX
    Explanations

    relative clauses that describe or provide additional information about a noun

    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
    ank
    -0.06
    /
    -0.06
     alleged
    -0.06
    -the
    -0.06
    :
    -0.06
     flair
    -0.06
    (s
    -0.05
    .
    -0.05
    yl
    -0.05
     Barcl
    -0.05
    POSITIVE LOGITS
    ëĵľë¦¬
    0.08
    μει
    0.08
    estre
    0.07
    sgi
    0.07
     sinh
    0.07
    enheim
    0.07
    azor
    0.07
    kowski
    0.07
    auge
    0.07
    ê¸
    0.07
    Activations Density 0.013%

    No Known Activations