© 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. 17-LLAMASCOPE-RES-131K
    11. 117687
    Prev
    Next
    INDEX
    Explanations

    descriptors related to color intensity and variations

    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
    sse
    -0.07
    agli
    -0.07
    cep
    -0.07
    asad
    -0.06
    ets
    -0.06
    olson
    -0.06
    ÅĤo
    -0.06
    844
    -0.06
    iasi
    -0.06
    amon
    -0.05
    POSITIVE LOGITS
    iator
    0.07
    EIF
    0.07
    liest
    0.07
     enough
    0.07
    ÑģÑĤеÑĢ
    0.07
    ål
    0.07
    ä¸Ī
    0.07
    UTERS
    0.07
    aylor
    0.07
    agne
    0.07
    Activations Density 0.012%

    No Known Activations