© 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. 75846
    Prev
    Next
    INDEX
    Explanations

    significant location-related terms and indicators of actions or decisions

    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
    ãģ«ãģ¦
    -0.07
    меÑĩ
    -0.06
     cannot
    -0.06
    Regards
    -0.06
    _ASSUME
    -0.06
    опаÑģ
    -0.06
    cannot
    -0.05
     Tradition
    -0.05
    stration
    -0.05
    ervice
    -0.05
    POSITIVE LOGITS
     basically
    0.07
    licos
    0.07
    reh
    0.07
     this
    0.07
    .getElements
    0.07
     yeah
    0.07
     pretty
    0.07
     big
    0.07
     vigor
    0.06
     really
    0.06
    Activations Density 0.000%

    No Known Activations