© 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. 58951
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to mathematical definitions and frameworks

    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
     OK
    -0.06
     ///<
    -0.06
    ahr
    -0.06
     Obs
    -0.06
     Nap
    -0.06
    142
    -0.06
    0
    -0.06
     ok
    -0.06
    gel
    -0.06
    apons
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.10
    /*č↵
    0.08
    .scalablytyped
    0.08
    .updateDynamic
    0.08
    _firestore
    0.07
    ĥn
    0.07
    OptionsResolver
    0.07
    -INF
    0.07
    HeaderCode
    0.07
     меÑĤалли
    0.07
    Activations Density 0.109%

    No Known Activations