© 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. 40355
    Prev
    Next
    INDEX
    Explanations

    content related to educational programs and events

    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
    ège
    -0.07
    ONO
    -0.06
     Huff
    -0.06
    uarios
    -0.06
    <this
    -0.06
     Crushers
    -0.06
    ħ§
    -0.06
     desp
    -0.06
    anco
    -0.05
    incinn
    -0.05
    POSITIVE LOGITS
    :↵
    0.30
    :↵↵
    0.24
     :↵
    0.23
    :č↵
    0.22
    ):↵
    0.21
    ":↵
    0.20
    ï¼ļ↵
    0.19
    å¦Ĥä¸ĭ
    0.18
    ':↵
    0.18
    :↵↵↵
    0.18
    Activations Density 0.314%

    No Known Activations