© 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. 124303
    Prev
    Next
    INDEX
    Explanations

    references to new music tracks and recordings

    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
    èĥİ
    -0.08
    etros
    -0.07
    lom
    -0.07
    RunWith
    -0.07
    ettes
    -0.06
    ноÑģи
    -0.06
    alue
    -0.06
    FRING
    -0.06
     Patch
    -0.06
     Successful
    -0.06
    POSITIVE LOGITS
     entitled
    0.07
     titled
    0.07
    ody
    0.07
     titul
    0.06
    alth
    0.06
    ód
    0.06
     ticking
    0.06
    anco
    0.06
     new
    0.06
    anni
    0.06
    Activations Density 0.012%

    No Known Activations