© 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. 70212
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypothetical scenarios or examples

    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
    nest
    -0.07
    elijk
    -0.07
    idak
    -0.06
    ipher
    -0.06
    ellig
    -0.06
    mile
    -0.06
    natal
    -0.06
     полÑı
    -0.06
    mic
    -0.06
    icas
    -0.06
    POSITIVE LOGITS
    455
    0.07
     sez
    0.07
    çķ¥
    0.06
    bette
    0.06
    ura
    0.06
     Cube
    0.06
    .ZERO
    0.06
    볨
    0.06
     Walk
    0.06
    _cu
    0.06
    Activations Density 0.001%

    No Known Activations