© 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. 39857
    Prev
    Next
    INDEX
    Explanations

    items that are organized or categorized with numerical identifiers

    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
    ainment
    -0.06
     Bol
    -0.06
     Niet
    -0.06
     rain
    -0.06
    afari
    -0.06
     Dipl
    -0.05
    afd
    -0.05
    kw
    -0.05
    avor
    -0.05
    alent
    -0.05
    POSITIVE LOGITS
    -number
    0.11
     номеÑĢ
    0.10
     numbered
    0.10
    ç¼ĸåı·
    0.09
     numbering
    0.09
    çķªåı·
    0.09
    åı·
    0.09
    æķ°åŃĹ
    0.08
     number
    0.08
    number
    0.08
    Activations Density 0.034%

    No Known Activations