© 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. 54965
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or specific terms related to various fields

    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
    icolor
    -0.07
    .Parcelable
    -0.06
    ardo
    -0.06
    ordo
    -0.06
    aura
    -0.06
    WithString
    -0.06
    iez
    -0.06
    _invoke
    -0.06
    invoke
    -0.06
    anlı
    -0.06
    POSITIVE LOGITS
    ye
    0.07
    CTR
    0.06
    åĪĹ
    0.06
     @@↵
    0.06
    utin
    0.06
    yyy
    0.06
     Corey
    0.06
    eri
    0.06
     Duffy
    0.06
    786
    0.06
    Activations Density 0.041%

    No Known Activations