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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79291
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to existence and processes within contexts of discussion

    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
     tslint
    -0.06
    òn
    -0.06
    ption
    -0.06
     geç
    -0.06
    ISOString
    -0.05
     flashing
    -0.05
    ones
    -0.05
    asia
    -0.05
    agar
    -0.05
    ptions
    -0.05
    POSITIVE LOGITS
     probably
    0.19
     possibly
    0.18
    probably
    0.18
     likely
    0.17
    likely
    0.17
     perhaps
    0.16
     maybe
    0.16
    possibly
    0.15
     seems
    0.15
    maybe
    0.14
    Activations Density 0.071%

    No Known Activations