© 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. 79277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating mathematical or scientific concepts related to modeling and relationships

    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
    velt
    -0.07
    apus
    -0.06
    467
    -0.06
    coli
    -0.06
    tae
    -0.06
     Eins
    -0.06
    eless
    -0.06
     NOTICE
    -0.06
     frames
    -0.06
    aque
    -0.06
    POSITIVE LOGITS
     Incre
    0.07
    /debug
    0.07
     McKin
    0.07
     specific
    0.06
    òng
    0.06
     anything
    0.06
    enet
    0.06
    imonial
    0.06
     jednotlivých
    0.06
    umin
    0.06
    Activations Density 0.058%

    No Known Activations