© 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. 127803
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "Library of" and related references

    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
    461
    -0.07
    iking
    -0.06
    uada
    -0.06
     åĿ
    -0.06
    atus
    -0.06
    err
    -0.06
    .contentType
    -0.06
    hil
    -0.06
    çĸĨ
    -0.06
    ÑĢек
    -0.06
    POSITIVE LOGITS
     dikke
    0.07
    YTE
    0.07
     палÑĮ
    0.06
    ancock
    0.06
    ivec
    0.06
    æ¡Ī
    0.06
    -session
    0.06
     Sector
    0.06
    580
    0.06
    anned
    0.06
    Activations Density 0.002%

    No Known Activations