© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84766
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptocurrency concepts and their differences

    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
    erto
    -0.08
    ardin
    -0.07
     Ernest
    -0.07
    [href
    -0.07
    acebook
    -0.06
    uj
    -0.06
    esium
    -0.06
    ayout
    -0.06
    eselect
    -0.06
     MethodInfo
    -0.06
    POSITIVE LOGITS
    Supply
    0.08
     Supply
    0.07
    IRT
    0.07
     supply
    0.07
     cap
    0.07
    anten
    0.07
    hle
    0.06
    responseData
    0.06
     circulating
    0.06
    enders
    0.06
    Activations Density 0.008%

    No Known Activations