© 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. 57793
    Prev
    Next
    INDEX
    Explanations

    key concepts and attributes related to noteworthy events or practices

    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
    ESCO
    -0.08
    lier
    -0.07
    anza
    -0.07
    oad
    -0.07
    uet
    -0.07
     showc
    -0.07
    illow
    -0.07
    ForRow
    -0.07
    .infinity
    -0.07
    RECT
    -0.07
    POSITIVE LOGITS
     unique
    0.11
     tick
    0.10
     apart
    0.09
     Unique
    0.09
    Unique
    0.08
     so
    0.08
     à¤ĩतन
    0.08
     special
    0.08
    unique
    0.08
     successful
    0.07
    Activations Density 0.021%

    No Known Activations