© 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. 89106
    Prev
    Next
    INDEX
    Explanations

    occurrences of academic phrases and structures indicating research findings or assumptions

    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
    dust
    -0.07
    esco
    -0.07
    ominator
    -0.06
     stain
    -0.06
    .sdk
    -0.06
    redient
    -0.06
    ÑĢовиÑĩ
    -0.06
    íĥĪ
    -0.06
    ŀĭ
    -0.06
    lease
    -0.06
    POSITIVE LOGITS
     scholarship
    0.07
     Scholarship
    0.07
    ively
    0.07
     Nep
    0.07
    ota
    0.07
    _firestore
    0.07
    aton
    0.06
     boon
    0.06
    Äįel
    0.06
    注
    0.06
    Activations Density 0.025%

    No Known Activations