© 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 EvalsExportsinterp-engineNEWAPI 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. 87709
    Prev
    Next
    INDEX
    Explanations

    monetary amounts, particularly in millions and billions

    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
    ball
    -0.07
    ILLE
    -0.07
    sy
    -0.07
    bew
    -0.07
    oom
    -0.06
    ras
    -0.06
    oms
    -0.06
    ually
    -0.06
    ĤŃ
    -0.06
    &E
    -0.06
    POSITIVE LOGITS
    aires
    0.12
    ì§ľ
    0.08
    -plus
    0.08
    isecond
    0.08
    ìĶ©
    0.07
    ths
    0.07
    aire
    0.07
    以ä¸Ĭ
    0.07
    å·¦åı³
    0.07
    olt
    0.07
    Activations Density 0.031%

    No Known Activations