© 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. 131011
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names or titles

    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
    osc
    -0.08
    SB
    -0.07
     Mane
    -0.07
    ázev
    -0.06
    grams
    -0.06
    .catalog
    -0.06
     minWidth
    -0.06
    OSC
    -0.06
    itives
    -0.06
     Osc
    -0.06
    POSITIVE LOGITS
    anza
    0.07
    SENS
    0.07
    ITERAL
    0.06
    .relationship
    0.06
    ège
    0.06
     Lite
    0.06
     Fritz
    0.06
    ìĤ¬ìĿĺ
    0.06
    iferay
    0.06
    obot
    0.06
    Activations Density 0.024%

    No Known Activations