© 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. 39947
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance or positive impact of projects or initiatives

    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
    uhl
    -0.07
    noloj
    -0.07
    <?,
    -0.07
     dor
    -0.07
    ãģ¡ãĤĥ
    -0.07
    γι
    -0.07
    ãĥ´
    -0.06
    ãģ«ãģ¨
    -0.06
    зÑĭ
    -0.06
    ĵåIJį
    -0.06
    POSITIVE LOGITS
    ovit
    0.06
    aday
    0.06
    igan
    0.06
    cep
    0.06
    iser
    0.06
    asu
    0.06
    ocu
    0.06
    è¾
    0.05
    opis
    0.05
    filled
    0.05
    Activations Density 0.014%

    No Known Activations