© 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. 15-LLAMASCOPE-RES-131K
    11. 86829
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" 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
    iable
    -0.07
    ÏĦιÏĥ
    -0.06
     rencont
    -0.06
    stadt
    -0.06
    .dw
    -0.06
    åŃĿ
    -0.06
    maj
    -0.06
    oup
    -0.06
     clocks
    -0.06
    _tA
    -0.06
    POSITIVE LOGITS
    /or
    0.10
    cul
    0.07
    rogen
    0.07
    hest
    0.07
    ifice
    0.06
     Angeles
    0.06
    atorio
    0.06
    943
    0.06
    944
    0.06
    ROID
    0.06
    Activations Density 0.020%

    No Known Activations