© 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. 81290
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "being" in various contexts

    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
    inka
    -0.07
    ff
    -0.06
    onn
    -0.06
    ÑĪов
    -0.06
    serrat
    -0.06
    pts
    -0.06
    onor
    -0.06
    atab
    -0.06
    isbury
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
    789
    0.07
     done
    0.07
    GIN
    0.07
     said
    0.07
    kest
    0.06
    ellipse
    0.06
    igin
    0.06
     happening
    0.06
    asty
    0.06
    icrobial
    0.06
    Activations Density 0.002%

    No Known Activations