© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83267
    Prev
    Next
    INDEX
    Explanations

    references to foundational concepts or essentials in procedural contexts

    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
    pery
    -0.08
    teg
    -0.07
    \grid
    -0.07
    æ¤
    -0.07
    uesta
    -0.07
    alah
    -0.07
    IIIK
    -0.07
    tek
    -0.07
    aldo
    -0.07
    _mt
    -0.06
    POSITIVE LOGITS
     need
    0.10
     added
    0.08
     usual
    0.07
     benefit
    0.07
     any
    0.07
     feeling
    0.07
     use
    0.07
     Rein
    0.06
     previously
    0.06
     same
    0.06
    Activations Density 0.009%

    No Known Activations