© 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. 16391
    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
    @nate
    -0.08
     UIStoryboard
    -0.08
    .scalablytyped
    -0.08
    alchemy
    -0.07
    æĹıèĩªæ²»
    -0.07
    Ìģ
    -0.07
    _permalink
    -0.07
    alon
    -0.07
     å¾ĴæŃ©
    -0.07
    OnInit
    -0.07
    POSITIVE LOGITS
     ke
    0.06
     everyone
    0.06
     h
    0.06
     Howell
    0.06
     pent
    0.06
     o
    0.06
    eldom
    0.06
    icha
    0.06
     freely
    0.06
    ovenant
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.