© 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. 117229
    Prev
    Next
    INDEX
    Explanations

    references to categorization or classification, particularly in relation to news or content sections

    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
    -0.08
    zac
    -0.08
    asco
    -0.07
    oster
    -0.07
     ><?
    -0.07
    conde
    -0.07
    acd
    -0.07
    à¹Ħà¸ĭà¸ķ
    -0.07
    _ENSURE
    -0.07
    lio
    -0.07
    POSITIVE LOGITS
    neath
    0.09
    unsch
    0.07
    lined
    0.07
    /out
    0.06
     section
    0.06
     under
    0.06
    lashes
    0.06
     “
    0.06
     each
    0.06
    enger
    0.06
    Activations Density 0.006%

    No Known Activations