© 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. 9-LLAMASCOPE-RES-131K
    11. 95582
    Prev
    Next
    INDEX
    Explanations

    terms related to academic positions and applications

    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
     Dut
    -0.07
    елÑĮзÑı
    -0.07
    ascus
    -0.07
     Incontri
    -0.07
    inci
    -0.06
    orelease
    -0.06
    appen
    -0.06
    едак
    -0.06
     Stam
    -0.06
    venes
    -0.06
    POSITIVE LOGITS
    anj
    0.06
     rub
    0.06
    ssc
    0.06
    avel
    0.06
    ://'
    0.05
    pj
    0.05
    anza
    0.05
    ist
    0.05
    .respond
    0.05
     ail
    0.05
    Activations Density 0.004%

    No Known Activations