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

    Neuronpedia

    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. 105700
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to organizations and locations

    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
    ecd
    -0.07
    reste
    -0.07
    agina
    -0.07
    añ
    -0.07
    ฺ
    -0.07
    itorio
    -0.07
    ála
    -0.07
    ambio
    -0.07
    ondo
    -0.07
    .serializer
    -0.07
    POSITIVE LOGITS
    486
    0.07
    -Compatible
    0.07
     fame
    0.06
     parent
    0.06
    665
    0.06
    .getContentPane
    0.06
     said
    0.06
     mess
    0.06
    770
    0.06
    Mess
    0.06
    Activations Density 0.026%

    No Known Activations