© 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. 120674
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or committees

    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
     nackte
    -0.08
    ITO
    -0.07
    zin
    -0.07
    chip
    -0.07
    rogen
    -0.07
    IGHLIGHT
    -0.07
    phis
    -0.06
    gtest
    -0.06
    rupa
    -0.06
    âĢ¢↵↵
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĥĪ
    0.07
    _UNLOCK
    0.06
    blank
    0.06
    é®
    0.06
    .learn
    0.06
    ivamente
    0.06
    axe
    0.06
    aks
    0.05
    (CharSequence
    0.05
    ÑĮко
    0.05
    Activations Density 0.398%

    No Known Activations