© 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. 17-LLAMASCOPE-RES-131K
    11. 117438
    Prev
    Next
    INDEX
    Explanations

    discussions around governance, economic policies, and social reforms

    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
     usually
    -0.06
    ãĥ©ãĤ¯
    -0.06
    rots
    -0.06
    TEL
    -0.06
    orp
    -0.06
    ãģĭãĤīãģ®
    -0.06
    assis
    -0.06
    orts
    -0.06
    bable
    -0.06
    ालà¤ķ
    -0.06
    POSITIVE LOGITS
    being
    0.08
    нÑĥÑĤÑĮ
    0.07
     be
    0.07
     плÑı
    0.07
    /disable
    0.07
     being
    0.07
    owaÄĩ
    0.07
     distra
    0.06
    nton
    0.06
     být
    0.06
    Activations Density 0.034%

    No Known Activations