© 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. 56228
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presented" and its variations in text

    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
    ola
    -0.07
     hun
    -0.06
     ple
    -0.06
     and
    -0.06
    åħ¶ä¸Ń
    -0.06
    er
    -0.05
    OLA
    -0.05
    oon
    -0.05
    ,
    -0.05
    f
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    iments
    0.08
     تÙĪÙĦ
    0.08
    ượng
    0.08
    ninger
    0.08
    ضÛĮ
    0.07
    ]âĢı
    0.07
    iment
    0.07
    WithContext
    0.07
     spons
    0.07
    Activations Density 0.003%

    No Known Activations