© 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. 76437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    bjerg
    -0.08
    issen
    -0.07
    antha
    -0.06
    obel
    -0.06
    ingers
    -0.06
     hafta
    -0.06
    zim
    -0.06
    716
    -0.06
    ì©
    -0.06
    rze
    -0.06
    POSITIVE LOGITS
    å½
    0.06
    asley
    0.06
    ulong
    0.06
    ãĥ³ãĤ¹
    0.06
    eria
    0.06
    ousse
    0.06
    nore
    0.06
    ãĢ
    0.06
    .win
    0.05
    λιά
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.