© 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. 15-LLAMASCOPE-RES-131K
    11. 61615
    Prev
    Next
    INDEX
    Explanations

    instances of repetition and continuity in themes or concepts

    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
    antis
    -0.08
    ostat
    -0.07
    IRO
    -0.07
    akedown
    -0.07
     vess
    -0.07
    äºĶæľĪ
    -0.07
    607
    -0.06
    iro
    -0.06
    پر
    -0.06
     ì°¬
    -0.06
    POSITIVE LOGITS
     audience
    0.08
     Audience
    0.06
     guests
    0.06
     rou
    0.06
    _lengths
    0.06
     guest
    0.06
    emme
    0.06
     audiences
    0.06
    setMax
    0.06
    ηγ
    0.06
    Activations Density 0.001%

    No Known Activations