© 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 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. 93963
    Prev
    Next
    INDEX
    Explanations

    words that indicate the introduction or presentation of people and concepts

    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
    264
    -0.07
    ÑĢÑĸд
    -0.07
    /im
    -0.07
    endi
    -0.07
    vek
    -0.07
    ocha
    -0.06
    .getEnd
    -0.06
    -mf
    -0.06
    dale
    -0.06
    ochen
    -0.06
    POSITIVE LOGITS
    iber
    0.07
     unfamiliar
    0.06
     concepts
    0.06
     Orientation
    0.06
    istar
    0.06
     kepada
    0.06
    uffs
    0.06
    ETA
    0.06
    bread
    0.06
     orient
    0.06
    Activations Density 0.007%

    No Known Activations