© 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. 129944
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight the best aspects or parts of experiences

    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
    arton
    -0.08
    æĿ¯
    -0.07
    acock
    -0.07
    laÄį
    -0.07
    ey
    -0.06
    eydi
    -0.06
    ypi
    -0.06
    chant
    -0.06
    -à¤ķ
    -0.06
    _SHAPE
    -0.06
    POSITIVE LOGITS
    veis
    0.06
    kara
    0.06
    itone
    0.06
    omi
    0.06
    823
    0.06
    rové
    0.06
    .scalablytyped
    0.06
     Francie
    0.06
    ÑıÑĤ
    0.06
    ximity
    0.06
    Activations Density 0.005%

    No Known Activations