© 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. 17-LLAMASCOPE-RES-131K
    11. 17029
    Prev
    Next
    INDEX
    Explanations

    references to programming objects and libraries

    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
    chein
    -0.07
    olio
    -0.07
    /animations
    -0.07
    ovol
    -0.07
    uchen
    -0.07
    .FindGameObjectWithTag
    -0.07
    toi
    -0.07
    ruba
    -0.07
    Å¡ov
    -0.07
    avis
    -0.07
    POSITIVE LOGITS
    .net
    0.07
    FromClass
    0.07
    (iOS
    0.07
    ÐIJÑĢÑħÑĸв
    0.06
    .com
    0.06
    icens
    0.06
    resse
    0.06
     inf
    0.06
    idot
    0.06
    .org
    0.06
    Activations Density 0.007%

    No Known Activations