© 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. 123642
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases indicating inquiry or propositions

    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
    osate
    -0.07
    ffen
    -0.07
    zim
    -0.07
    cust
    -0.07
     Flat
    -0.07
    ÅĽnie
    -0.06
    ائÙħØ©
    -0.06
    oglob
    -0.06
    rish
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
    .future
    0.07
     answered
    0.07
    çŃĶæ¡Ī
    0.06
    /foo
    0.06
    _pm
    0.06
     Ãĸn
    0.06
     varsa
    0.06
     Lun
    0.06
    dera
    0.06
     convolution
    0.06
    Activations Density 0.003%

    No Known Activations