© 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. 117560
    Prev
    Next
    INDEX
    Explanations

    references to locations and time frames in narratives

    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
    Ø°
    -0.07
     klu
    -0.06
    íķĺìļ°
    -0.06
    ÄĻż
    -0.06
     обÑģÑĤ
    -0.06
    etch
    -0.06
     norge
    -0.06
     Markets
    -0.06
    andle
    -0.06
     headlights
    -0.06
    POSITIVE LOGITS
     occasion
    0.08
     Roose
    0.07
     detriment
    0.07
    adera
    0.07
     AssemblyVersion
    0.07
    eway
    0.07
     occasions
    0.06
    .dsl
    0.06
     behalf
    0.06
    onn
    0.06
    Activations Density 0.157%

    No Known Activations