© 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. 89077
    Prev
    Next
    INDEX
    Explanations

    references to future events or predictions

    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
    phem
    -0.07
    stant
    -0.07
    858
    -0.06
    adia
    -0.06
    oles
    -0.06
    ote
    -0.06
    erture
    -0.06
    stoi
    -0.06
    ÑĮко
    -0.06
    imb
    -0.06
    POSITIVE LOGITS
     luc
    0.07
     tense
    0.07
    alon
    0.06
    auss
    0.06
    rs
    0.06
    SY
    0.06
    $$$$
    0.06
     BAS
    0.06
    Luc
    0.06
    aland
    0.06
    Activations Density 0.002%

    No Known Activations