© 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. 80315
    Prev
    Next
    INDEX
    Explanations

    variations in data or situations across different contexts

    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
    inch
    -0.09
    æµľ
    -0.07
    ipay
    -0.07
     Weiss
    -0.07
    kem
    -0.06
    evin
    -0.06
    rana
    -0.06
    campo
    -0.06
    kontakte
    -0.06
    anou
    -0.06
    POSITIVE LOGITS
     depending
    0.14
    depending
    0.11
     Depending
    0.09
     depends
    0.08
     depend
    0.07
    Depending
    0.07
    depends
    0.07
     whether
    0.07
     dependent
    0.07
    whether
    0.07
    Activations Density 0.023%

    No Known Activations