© 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. 88854
    Prev
    Next
    INDEX
    Explanations

    web links and online tracking information

    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
    curities
    -0.08
    ylland
    -0.07
    allis
    -0.07
    ilis
    -0.07
    Interop
    -0.07
    ç£
    -0.06
    thora
    -0.06
    antan
    -0.06
    okane
    -0.06
    ^.
    -0.06
    POSITIVE LOGITS
     Commission
    0.09
     commission
    0.08
     affiliate
    0.07
    Commission
    0.07
     affiliates
    0.06
     commissions
    0.06
    ¢åįķ
    0.06
     Affiliate
    0.06
    afil
    0.06
     flat
    0.06
    Activations Density 0.007%

    No Known Activations