© 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. 77986
    Prev
    Next
    INDEX
    Explanations

    objects or items with significant visual or thematic prominence

    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
     everything
    -0.07
     pri
    -0.06
    rage
    -0.06
    258
    -0.06
    618
    -0.05
    rique
    -0.05
     the
    -0.05
     often
    -0.05
     even
    -0.05
    hood
    -0.05
    POSITIVE LOGITS
    /inet
    0.09
    etsk
    0.08
    éIJĺ
    0.08
    conds
    0.07
    anceled
    0.07
    LError
    0.07
     GOODMAN
    0.07
    bersome
    0.07
    lops
    0.07
    OfDay
    0.07
    Activations Density 0.075%

    No Known Activations