© 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. 78416
    Prev
    Next
    INDEX
    Explanations

    the pronoun "it" and associated references, reflecting the use of that term in varied 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
    illac
    -0.07
     Leban
    -0.06
    clearfix
    -0.06
    .tp
    -0.06
    UMAN
    -0.06
    rray
    -0.06
    orean
    -0.06
    ÙĪÙĦا
    -0.06
    ords
    -0.06
     Kurd
    -0.06
    POSITIVE LOGITS
    iner
    0.10
     happening
    0.08
    awy
    0.07
    chy
    0.07
     Cly
    0.06
    ngör
    0.06
    (DIS
    0.06
     being
    0.06
    717
    0.06
     seedu
    0.06
    Activations Density 0.030%

    No Known Activations