© 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. 104370
    Prev
    Next
    INDEX
    Explanations

    hyperlinks in the text

    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
    ÑĨÑĸв
    -0.06
    sez
    -0.06
     Hedge
    -0.06
    drops
    -0.06
     br
    -0.06
    541
    -0.06
    holm
    -0.05
    morgan
    -0.05
     Hed
    -0.05
    876
    -0.05
    POSITIVE LOGITS
    ihat
    0.07
    URN
    0.07
    orgen
    0.07
    ült
    0.07
    agram
    0.07
     Coat
    0.06
    nul
    0.06
    ichten
    0.06
    okt
    0.06
    iag
    0.06
    Activations Density 0.001%

    No Known Activations