© 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. 41470
    Prev
    Next
    INDEX
    Explanations

    instances of matching or correspondence between elements or concepts

    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
    oise
    -0.07
    ESS
    -0.06
    ’
    -0.06
     unspecified
    -0.06
    ba
    -0.06
    illac
    -0.06
    '
    -0.06
    CG
    -0.06
     fora
    -0.06
    AYS
    -0.05
    POSITIVE LOGITS
     ones
    0.11
     corres
    0.10
     corresponding
    0.09
     correspond
    0.09
     ÑģооÑĤвеÑĤ
    0.08
     Ones
    0.08
     correspondent
    0.08
    endor
    0.08
     ÑģооÑĤвеÑĤÑģÑĤв
    0.07
    óng
    0.07
    Activations Density 0.069%

    No Known Activations