© 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. 60747
    Prev
    Next
    INDEX
    Explanations

    negations or negative phrases

    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
    chner
    -0.07
     sec
    -0.06
    orra
    -0.06
    voj
    -0.06
    fst
    -0.06
     nues
    -0.06
    stit
    -0.06
    pg
    -0.06
    edBy
    -0.06
    -transitional
    -0.06
    POSITIVE LOGITS
     everyone
    0.09
    ieder
    0.08
    iced
    0.07
     everybody
    0.07
    tl
    0.07
    HIR
    0.07
    ices
    0.07
    erdale
    0.07
    hsi
    0.07
    everyone
    0.07
    Activations Density 0.013%

    No Known Activations