© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    phrases involving expressions of opinion or assertion

    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
    usk
    -0.08
    inheritDoc
    -0.07
    ÅĻes
    -0.07
    ylon
    -0.07
     Laugh
    -0.07
    yonel
    -0.07
    ÅĻez
    -0.07
    gis
    -0.07
    reature
    -0.07
    ä¿
    -0.06
    POSITIVE LOGITS
     necessarily
    0.11
     anymore
    0.06
    estre
    0.06
    ENA
    0.06
     either
    0.06
     entirely
    0.06
     fault
    0.06
     immediately
    0.06
    erm
    0.06
    tap
    0.06
    Activations Density 0.009%

    No Known Activations