© 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. 15313
    Prev
    Next
    INDEX
    Explanations

    descriptions related to company registration and status

    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
    osate
    -0.08
    anship
    -0.06
    ining
    -0.06
    bons
    -0.06
    elo
    -0.06
     dit
    -0.06
    ela
    -0.06
    anga
    -0.06
    761
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
    hind
    0.07
    peq
    0.07
     address
    0.06
    DEM
    0.06
    iez
    0.06
    ÐļТ
    0.06
     incorpor
    0.06
     dissolve
    0.06
    address
    0.06
    itler
    0.06
    Activations Density 0.003%

    No Known Activations