© 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. 89097
    Prev
    Next
    INDEX
    Explanations

    phrases related to inquiries or responses from involved parties

    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
    ÅĽcie
    -0.07
    kip
    -0.07
    ↵↵
    -0.06
    kers
    -0.06
    osto
    -0.06
    our
    -0.06
    iten
    -0.06
     automatically
    -0.06
     predict
    -0.06
    chner
    -0.06
    POSITIVE LOGITS
     reply
    0.07
    uce
    0.07
    िण
    0.06
    429
    0.06
     Tomorrow
    0.06
    _pag
    0.06
    isci
    0.06
    ponce
    0.06
     complete
    0.06
    dere
    0.06
    Activations Density 0.010%

    No Known Activations