© 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. 85622
    Prev
    Next
    INDEX
    Explanations

    instances of celebrity names and significant cultural events

    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
    ãĥ³ãĥĦ
    -0.07
    (=)
    -0.07
    окол
    -0.07
    ÏĢÎŃ
    -0.06
    PEnd
    -0.06
    ãģĭãģij
    -0.06
    ombok
    -0.06
    //**↵
    -0.06
     DEALINGS
    -0.06
     myself
    -0.06
    POSITIVE LOGITS
     Plus
    0.08
    Plus
    0.08
     plus
    0.07
     UPDATED
    0.07
     only
    0.07
     It
    0.07
     Also
    0.07
     it
    0.07
    ksam
    0.06
     also
    0.06
    Activations Density 0.015%

    No Known Activations