© 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. 107258
    Prev
    Next
    INDEX
    Explanations

    references to brands, products, and company-related details

    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
    642
    -0.08
    agma
    -0.07
    QualifiedName
    -0.07
    ekl
    -0.07
    isma
    -0.07
    wie
    -0.07
    _HAVE
    -0.06
    asca
    -0.06
    suz
    -0.06
    iu
    -0.06
    POSITIVE LOGITS
     official
    0.08
     publicly
    0.08
     directly
    0.08
     oficial
    0.07
     direct
    0.07
     Official
    0.07
    official
    0.07
    å®ĺæĸ¹
    0.07
     sources
    0.06
    onas
    0.06
    Activations Density 0.014%

    No Known Activations