© 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. 4799
    Prev
    Next
    INDEX
    Explanations

    concepts related to depth and underlying themes in narratives

    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
    ris
    -0.07
    blr
    -0.07
    ibName
    -0.07
    ekl
    -0.07
    /trunk
    -0.07
    éf
    -0.07
     Contrast
    -0.07
    elper
    -0.06
    ibel
    -0.06
    izr
    -0.06
    POSITIVE LOGITS
     surface
    0.13
     layers
    0.10
     appearances
    0.10
     vene
    0.10
     layer
    0.10
     Surface
    0.10
    surface
    0.10
     facade
    0.09
    layer
    0.09
    Surface
    0.08
    Activations Density 0.017%

    No Known Activations