© 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. 93247
    Prev
    Next
    INDEX
    Explanations

    the word "Unlike" in various 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
    oves
    -0.07
    atti
    -0.07
     Äiji
    -0.07
    ãģĨãģ¡
    -0.07
     seguint
    -0.07
    oba
    -0.07
    ť
    -0.07
    å¯
    -0.06
    §
    -0.06
     behalf
    -0.06
    POSITIVE LOGITS
     other
    0.10
     many
    0.09
     previous
    0.09
     typical
    0.08
     those
    0.07
     most
    0.07
     usual
    0.07
    many
    0.07
     others
    0.07
     some
    0.07
    Activations Density 0.006%

    No Known Activations