© 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. 119801
    Prev
    Next
    INDEX
    Explanations

    references to educational assessments and their revisions

    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
    adir
    -0.08
    ocht
    -0.07
    estar
    -0.07
    /pm
    -0.06
    lech
    -0.06
    Äĥng
    -0.06
    ISTR
    -0.06
     Pru
    -0.06
    ÙħاÙĨÛĮ
    -0.06
    [,]
    -0.06
    POSITIVE LOGITS
     season
    0.07
    ico
    0.06
    aison
    0.06
    aling
    0.06
    Cache
    0.06
    íĥĿ
    0.06
    Chan
    0.06
     mùa
    0.06
    æ²Ł
    0.06
    /assets
    0.06
    Activations Density 0.005%

    No Known Activations