© 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. 42163
    Prev
    Next
    INDEX
    Explanations

    expressions indicating progress or direction

    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
    agon
    -0.07
    gon
    -0.07
    assen
    -0.06
    .lu
    -0.06
    ấu
    -0.06
    /constants
    -0.06
    immer
    -0.06
    Dims
    -0.06
     muh
    -0.06
    bomb
    -0.06
    POSITIVE LOGITS
     towards
    0.08
     toward
    0.08
    .LayoutStyle
    0.07
    adget
    0.07
    reib
    0.06
    ozem
    0.06
    CppType
    0.06
    174
    0.06
    лÑĸв
    0.06
    enne
    0.06
    Activations Density 0.002%

    No Known Activations