© 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. 60399
    Prev
    Next
    INDEX
    Explanations

    keywords related to applications and costs associated with activities or events

    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
    SourceType
    -0.06
    deen
    -0.06
    _resolver
    -0.06
    èĩ
    -0.06
    apy
    -0.06
    rop
    -0.06
    .wikipedia
    -0.06
    -peer
    -0.06
    markup
    -0.06
    atched
    -0.06
    POSITIVE LOGITS
     Facility
    0.08
     facilities
    0.07
     Facilities
    0.07
     prospect
    0.07
    elik
    0.07
    chap
    0.07
     profile
    0.07
    çĵľ
    0.07
     talent
    0.07
     facility
    0.06
    Activations Density 0.000%

    No Known Activations