© 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. 28229
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or structures in a narrative 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
    icens
    -0.08
    ãģĤãĤĭ
    -0.08
    uien
    -0.08
    ãģĬ
    -0.07
    agnar
    -0.07
     yên
    -0.07
    PÅĻi
    -0.07
    rst
    -0.07
    ãģĤãĤĬ
    -0.07
    .qual
    -0.07
    POSITIVE LOGITS
    ching
    0.09
    oping
    0.09
    ched
    0.09
     has
    0.08
    upon
    0.08
     is
    0.08
     we
    0.07
    sembl
    0.07
    soever
    0.07
    ch
    0.07
    Activations Density 0.219%

    No Known Activations