© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74603
    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
    ¶Į
    -0.07
    nip
    -0.07
     congr
    -0.07
    rib
    -0.06
    intendo
    -0.06
    SWG
    -0.06
    erialize
    -0.06
    itty
    -0.06
     nackte
    -0.06
    //{{
    -0.06
    POSITIVE LOGITS
    antar
    0.06
    èĬ
    0.06
     Kraj
    0.06
    irs
    0.06
    igli
    0.06
    ambre
    0.06
    lesi
    0.06
    bjerg
    0.06
    zl
    0.06
    pper
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.