© 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. 75420
    Prev
    Next
    INDEX
    Explanations

    concepts related to claims and estimates in various contexts

    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
    cis
    -0.07
    endor
    -0.06
    dum
    -0.06
     Gang
    -0.06
    éĥİ
    -0.06
    otti
    -0.06
    gew
    -0.06
    iego
    -0.06
     Leather
    -0.06
    âĢ¦↵
    -0.06
    POSITIVE LOGITS
    ฯ
    0.09
    ãĥªãĤ«
    0.08
    oins
    0.08
    åŃĿ
    0.07
    _ISR
    0.07
    ç½
    0.07
    .setViewport
    0.07
    ÅĻejmÄĽ
    0.07
    ضÙħ
    0.07
     èĢ
    0.06
    Activations Density 0.050%

    No Known Activations