© 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. 9-LLAMASCOPE-RES-131K
    11. 95527
    Prev
    Next
    INDEX
    Explanations

    contexts related to features and benefits of products or experiences

    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
    ifter
    -0.07
     ÄijÃŃch
    -0.07
    à¥įश
    -0.07
    تÙĬÙĨ
    -0.07
    lse
    -0.07
    ë°°
    -0.07
    ìŀĦ
    -0.07
    asd
    -0.06
     seksi
    -0.06
    orks
    -0.06
    POSITIVE LOGITS
    olas
    0.06
    idar
    0.06
    è¯Ŀ
    0.06
    лика
    0.06
    ensburg
    0.05
    ingga
    0.05
    ossal
    0.05
     Russell
    0.05
     Prescott
    0.05
    ĥn
    0.05
    Activations Density 0.054%

    No Known Activations