© 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. 15-LLAMASCOPE-RES-131K
    11. 104189
    Prev
    Next
    INDEX
    Explanations

    nouns related to entities or roles in various contexts

    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
     everywhere
    -0.07
    们
    -0.07
    .are
    -0.07
     and
    -0.07
    lÃŃ
    -0.06
     aren
    -0.06
     же
    -0.06
     are
    -0.06
     subject
    -0.06
     various
    -0.06
    POSITIVE LOGITS
    cola
    0.07
    ãĢģä¸Ģ
    0.07
    gow
    0.07
    ettle
    0.07
    esti
    0.07
    erah
    0.07
    IDA
    0.07
    531
    0.07
    bedo
    0.07
    arda
    0.06
    Activations Density 0.042%

    No Known Activations