© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16495
    Prev
    Next
    INDEX
    Explanations

    terms related to embedding in various contexts

    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
    ÌĨ
    -0.07
    eland
    -0.07
    anger
    -0.07
    erie
    -0.06
    loom
    -0.06
    oner
    -0.06
    udge
    -0.06
    _restore
    -0.06
    inea
    -0.06
     Mellon
    -0.06
    POSITIVE LOGITS
    /embed
    0.13
    .embed
    0.09
    ding
    0.09
    ded
    0.09
    (embed
    0.08
    dings
    0.08
    Into
    0.08
    /Internal
    0.08
    å¼ı
    0.07
    /object
    0.07
    Activations Density 0.008%

    No Known Activations