© 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. 60138
    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
    zyst
    -0.06
    indy
    -0.06
     individual
    -0.06
     overall
    -0.06
    enties
    -0.06
    Tot
    -0.06
     [=
    -0.06
     Ø£ÙĬض
    -0.06
    adh
    -0.06
    ónico
    -0.06
    POSITIVE LOGITS
    åĥķ
    0.07
     imagined
    0.07
    <decltype
    0.06
     kola
    0.06
    elix
    0.06
     Stall
    0.06
    à¥ģà¤Ń
    0.06
    pone
    0.06
     english
    0.06
    олж
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.