© 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. 31065
    Prev
    Next
    INDEX
    Explanations

    descriptions of products or experiences with a focus on accessibility and enjoyment for a wide range of consumers

    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
    (Arg
    -0.06
    onga
    -0.06
    biology
    -0.06
    Americ
    -0.06
    inces
    -0.06
    ante
    -0.06
    yle
    -0.06
     Gro
    -0.06
    oze
    -0.06
    chedulers
    -0.06
    POSITIVE LOGITS
     targeting
    0.09
     dla
    0.09
     cater
    0.08
     dÃłnh
    0.08
     appeals
    0.07
     bagi
    0.07
     catering
    0.07
     appeal
    0.07
    สำหร
    0.07
     длÑı
    0.07
    Activations Density 0.044%

    No Known Activations