© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27225
    Prev
    Next
    INDEX
    Explanations

    indicators of service quality and pricing in repair and hospitality 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
    ozem
    -0.08
    éru
    -0.07
    éal
    -0.07
    andest
    -0.06
    panse
    -0.06
    à¹ģล
    -0.06
    anko
    -0.06
    erdale
    -0.06
    ylland
    -0.06
    okud
    -0.06
    POSITIVE LOGITS
    izm
    0.06
    _charset
    0.06
    lus
    0.06
     views
    0.06
    lish
    0.06
    auen
    0.06
    croft
    0.06
    iji
    0.06
     Luther
    0.06
    _pdf
    0.06
    Activations Density 0.022%

    No Known Activations