© 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 EvalsExportsAPI 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. 85927
    Prev
    Next
    INDEX
    Explanations

    specific brand names or product identifiers

    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
    'gc
    -0.08
    isci
    -0.08
     lParam
    -0.07
    lehem
    -0.07
    apgolly
    -0.07
    arsers
    -0.07
    ncia
    -0.07
    herits
    -0.07
    Ïĥμα
    -0.07
    ijken
    -0.07
    POSITIVE LOGITS
    s
    0.07
    er
    0.07
    oop
    0.07
    pp
    0.06
    vier
    0.06
    sik
    0.06
    iciency
    0.06
     Ell
    0.06
    Ùij
    0.06
     sw
    0.06
    Activations Density 0.055%

    No Known Activations