© 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. 28625
    Prev
    Next
    INDEX
    Explanations

    biological and evolutionary concepts related to genes and proteins

    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
    ẩu
    -0.08
    lemn
    -0.07
     statewide
    -0.07
    antine
    -0.07
     provincial
    -0.07
    odiac
    -0.07
    lope
    -0.06
    anson
    -0.06
    ,copy
    -0.06
     antagonist
    -0.06
    POSITIVE LOGITS
     species
    0.09
     Species
    0.07
     humans
    0.07
    Species
    0.07
    uss
    0.07
    species
    0.07
    blr
    0.06
    pecies
    0.06
     representatives
    0.06
    -human
    0.06
    Activations Density 0.065%

    No Known Activations