© 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. 106920
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and future projections

    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
    ndef
    -0.08
    bsolute
    -0.08
    usercontent
    -0.07
    ogan
    -0.07
    tring
    -0.07
    adar
    -0.07
    typings
    -0.07
    ilip
    -0.06
    kiego
    -0.06
    .sb
    -0.06
    POSITIVE LOGITS
     future
    0.08
    atti
    0.07
     months
    0.06
     tomorrow
    0.06
     few
    0.06
    æľªæĿ¥
    0.06
    lesc
    0.06
    ody
    0.06
     couple
    0.05
     weeks
    0.05
    Activations Density 0.008%

    No Known Activations