Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82945
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biological processes or substances

    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
    pter
    -0.07
    ovit
    -0.06
    ucci
    -0.06
    sten
    -0.06
    GEST
    -0.06
    oran
    -0.06
    igan
    -0.06
    sters
    -0.06
    ivid
    -0.06
    stro
    -0.06
    POSITIVE LOGITS
    ebb
    0.08
    OUS
    0.07
    tÃŃ
    0.07
    ysi
    0.07
    abis
    0.07
    _IRQ
    0.07
    ation
    0.07
    ácil
    0.06
    uml
    0.06
    DataExchange
    0.06
    Activations Density 0.000%

    No Known Activations