© 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. 86237
    Prev
    Next
    INDEX
    Explanations

    various indicators of dates, times, or related numerical 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
    pon
    -0.07
    LError
    -0.07
    affle
    -0.06
     Associates
    -0.06
    wagon
    -0.06
    çŃ
    -0.06
    eds
    -0.06
    ya
    -0.06
    umbo
    -0.06
    enos
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    zew
    0.07
     EXEMPLARY
    0.07
    elper
    0.07
    presso
    0.07
    ç·Ĵ
    0.06
    IGHL
    0.06
     Rath
    0.06
    è¤
    0.06
    ecz
    0.06
    Activations Density 0.012%

    No Known Activations