© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    terms related to artistic or intellectual expression

    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
    edback
    -0.09
     visite
    -0.07
     harmony
    -0.07
    AU
    -0.07
    仲
    -0.07
    azu
    -0.06
    zen
    -0.06
     cigaret
    -0.06
    ıt
    -0.06
    ajas
    -0.06
    POSITIVE LOGITS
     ourselves
    0.07
    jak
    0.07
    readcr
    0.06
    Stub
    0.06
     Rosa
    0.06
     maybe
    0.06
    INA
    0.06
     Adj
    0.06
    esium
    0.06
     defeats
    0.06
    Activations Density 0.001%

    No Known Activations