© 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. 15-LLAMASCOPE-RES-131K
    11. 27720
    Prev
    Next
    INDEX
    Explanations

    references to collaboration or partnership

    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
    bic
    -0.07
    梨
    -0.06
    bread
    -0.06
     RectTransform
    -0.06
    fontsize
    -0.06
    ailer
    -0.06
    afil
    -0.06
    æĨ¶
    -0.06
    ligne
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
     Color
    0.08
     color
    0.07
    heim
    0.07
    adder
    0.07
    Color
    0.07
    _color
    0.07
     COLOR
    0.07
    æ´¾
    0.07
    color
    0.06
     ê°Ŀ
    0.06
    Activations Density 0.000%

    No Known Activations