© 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. 78953
    Prev
    Next
    INDEX
    Explanations

    references to gaps and deficiencies in data or knowledge

    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
     addCriterion
    -0.10
    anlı
    -0.08
    togroup
    -0.08
    NewProp
    -0.08
    жен
    -0.08
    .§
    -0.08
    ãĤ¤ãĥ³ãĥĪ
    -0.08
    /license
    -0.07
    sik
    -0.07
    ActivityIndicatorView
    -0.07
    POSITIVE LOGITS
     understanding
    0.09
     system
    0.08
     coverage
    0.07
     existing
    0.07
     incomplete
    0.07
     inadequate
    0.07
     current
    0.07
     understand
    0.07
     perfection
    0.07
     plan
    0.06
    Activations Density 0.022%

    No Known Activations