© 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 EvalsExportsinterp-engineNEWAPI 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. 38867
    Prev
    Next
    INDEX
    Explanations

    references to specific products or technical specifications

    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
    neau
    -0.07
    594
    -0.06
     BigNumber
    -0.06
    fang
    -0.06
     Ä°ng
    -0.06
     autonomous
    -0.06
    anoia
    -0.06
    anga
    -0.06
     dil
    -0.06
    579
    -0.06
    POSITIVE LOGITS
    аниÑĨ
    0.07
     stra
    0.07
    çĩķ
    0.07
    .writeObject
    0.07
    uyá»ĩt
    0.07
    çīĮ
    0.07
     premium
    0.07
    UNCH
    0.07
    DEPTH
    0.07
     performance
    0.07
    Activations Density 0.066%

    No Known Activations