© 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. 15-LLAMASCOPE-RES-131K
    11. 87747
    Prev
    Next
    INDEX
    Explanations

    technical language related to data storage and processing

    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
    aget
    -0.06
     Caught
    -0.06
    upe
    -0.06
     ruku
    -0.06
    fresh
    -0.06
    sdale
    -0.06
    XMLElement
    -0.06
     Roller
    -0.05
    quarter
    -0.05
    каз
    -0.05
    POSITIVE LOGITS
    rál
    0.07
     STORAGE
    0.06
    çĶ
    0.06
    SocketAddress
    0.06
    Playback
    0.06
    oj
    0.06
    adil
    0.06
    ìłĿ
    0.06
    Fld
    0.06
    arter
    0.06
    Activations Density 0.001%

    No Known Activations