© 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. 17989
    Prev
    Next
    INDEX
    Explanations

    references to Arab identity and culture

    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
    Ñĸ
    -0.06
    sel
    -0.06
    Ñģ
    -0.06
    ory
    -0.06
     trust
    -0.06
    еÑĢ
    -0.06
     Carly
    -0.05
    igans
    -0.05
    PT
    -0.05
     d
    -0.05
    POSITIVE LOGITS
    ]âĢı
    0.10
    DataExchange
    0.09
    RuntimeObject
    0.09
    togroup
    0.09
    .LA
    0.09
    isContained
    0.08
    orelease
    0.08
    /goto
    0.08
    using
    0.08
     addCriterion
    0.08
    Activations Density 0.005%

    No Known Activations