© 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. 117076
    Prev
    Next
    INDEX
    Explanations

    HTML title tags and metadata elements

    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
    esktop
    -0.08
    antro
    -0.07
    olini
    -0.07
    conti
    -0.07
    769
    -0.06
    695
    -0.06
    ifo
    -0.06
    بات
    -0.06
    &o
    -0.06
    ikut
    -0.06
    POSITIVE LOGITS
    efon
    0.08
    ToLocal
    0.06
    ENDOR
    0.06
    vented
    0.06
    ictor
    0.06
    auge
    0.06
     Sür
    0.06
     RedirectTo
    0.06
    .accuracy
    0.06
    çľł
    0.06
    Activations Density 0.000%

    No Known Activations