© 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 EvalsExportsAPI 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. 130760
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and structures

    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
     bey
    -0.07
    æ³Ĭ
    -0.06
     Kraj
    -0.06
     mech
    -0.06
    .addField
    -0.06
    è°
    -0.06
     tas
    -0.06
    orage
    -0.06
     tower
    -0.06
     Ùħخت
    -0.06
    POSITIVE LOGITS
     surfaces
    0.08
    ivet
    0.07
     surface
    0.07
    osal
    0.07
     segments
    0.07
     Points
    0.06
    points
    0.06
    ein
    0.06
    egal
    0.06
     Soph
    0.06
    Activations Density 0.079%

    No Known Activations