© 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. 104254
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to structure and dimensionality

    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
     verv
    -0.07
    kır
    -0.07
    umi
    -0.07
    IFS
    -0.07
    819
    -0.07
    phan
    -0.07
    ephy
    -0.06
    ijd
    -0.06
    mana
    -0.06
    -strokes
    -0.06
    POSITIVE LOGITS
     ones
    0.08
     nature
    0.08
    imar
    0.07
     Ones
    0.07
    nature
    0.06
     meaning
    0.06
    reau
    0.06
    ymous
    0.06
    halb
    0.06
    isch
    0.06
    Activations Density 0.053%

    No Known Activations