© 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. 75099
    Prev
    Next
    INDEX
    Explanations

    references to personal identification and privacy

    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
    tdown
    -0.06
    lord
    -0.06
    ispens
    -0.06
     Han
    -0.06
    à¥įरय
    -0.06
    olt
    -0.06
    ieber
    -0.06
    -0.06
     Desire
    -0.06
    ursday
    -0.05
    POSITIVE LOGITS
    assis
    0.09
    XmlNode
    0.07
    ENN
    0.07
    liga
    0.07
    eut
    0.06
     pied
    0.06
    eltas
    0.06
     tablesp
    0.06
    amm
    0.06
    ikk
    0.06
    Activations Density 0.000%

    No Known Activations