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

    Neuronpedia

    Jacobian LensNEW
    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. 88711
    Prev
    Next
    INDEX
    Explanations

    job-related opportunities and descriptions

    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
    Enlarge
    -0.07
    FI
    -0.07
    .us
    -0.06
     Huff
    -0.06
    æ¥
    -0.06
    438
    -0.06
    æı
    -0.06
     ÙģÙĤ
    -0.05
    fi
    -0.05
     hardly
    -0.05
    POSITIVE LOGITS
    Salary
    0.07
     Salary
    0.07
    ipay
    0.07
    morgan
    0.07
    orden
    0.07
     salary
    0.07
    salary
    0.07
    udit
    0.07
    ê¸ī
    0.07
    aeda
    0.06
    Activations Density 0.006%

    No Known Activations