© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90138
    Prev
    Next
    INDEX
    Explanations

    high-frequency connector words and phrases that imply conditions or stipulations

    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
    enge
    -0.08
    zi
    -0.07
    being
    -0.07
     being
    -0.07
    deo
    -0.07
    iaz
    -0.07
    uje
    -0.07
    æī£
    -0.07
    ongan
    -0.07
    ittal
    -0.06
    POSITIVE LOGITS
    COME
    0.07
    cken
    0.07
    veled
    0.07
    fits
    0.06
    ially
    0.06
    ÐĿÐĨ
    0.06
    .yang
    0.06
     sole
    0.06
    UCH
    0.06
    stride
    0.06
    Activations Density 0.273%

    No Known Activations