© 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. 129780
    Prev
    Next
    INDEX
    Explanations

    technical terms and versioning information related to software distributions

    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
     intent
    -0.08
    achs
    -0.08
    vais
    -0.07
    iminal
    -0.07
    oog
    -0.07
     Intent
    -0.07
    .cb
    -0.07
    aurus
    -0.07
    ied
    -0.07
    rego
    -0.07
    POSITIVE LOGITS
     Haley
    0.07
    иденÑĤ
    0.07
     arenas
    0.06
    posting
    0.06
     mercy
    0.06
     arena
    0.06
    /layout
    0.06
    SG
    0.06
     Boone
    0.06
    unknown
    0.05
    Activations Density 0.006%

    No Known Activations