© 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. 17-LLAMASCOPE-RES-131K
    11. 17152
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names, particularly in a scholarly or academic context

    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
    lete
    -0.08
    ALSE
    -0.08
    ocz
    -0.08
    lum
    -0.07
    ilet
    -0.07
    acle
    -0.07
    imore
    -0.07
    ascus
    -0.07
    Schedulers
    -0.07
     Ø´Ùħ
    -0.07
    POSITIVE LOGITS
    ez
    0.08
    iola
    0.07
    ei
    0.07
    outu
    0.07
    scape
    0.07
    ray
    0.06
    ves
    0.06
    ếu
    0.06
    s
    0.06
    quist
    0.06
    Activations Density 0.022%

    No Known Activations