© 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. 15-LLAMASCOPE-RES-131K
    11. 86677
    Prev
    Next
    INDEX
    Explanations

    expressions of comprehension and awareness

    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
    ared
    -0.07
    let
    -0.07
    iyi
    -0.06
     hyp
    -0.06
     lax
    -0.06
    per
    -0.06
     elev
    -0.06
    von
    -0.06
    ey
    -0.06
     bite
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    cü
    0.09
    >NN
    0.08
    senal
    0.07
    idar
    0.07
    oldem
    0.07
    hma
    0.07
     kterým
    0.07
    entionPolicy
    0.07
    üc
    0.07
    Activations Density 0.033%

    No Known Activations