© 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. 28004
    Prev
    Next
    INDEX
    Explanations

    coding language structures related to deprecation

    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
    olls
    -0.06
    dra
    -0.06
    idata
    -0.06
    oto
    -0.06
    porto
    -0.06
    èªį
    -0.06
    ioso
    -0.06
    abor
    -0.06
     fry
    -0.06
    erson
    -0.06
    POSITIVE LOGITS
    سÙĪ
    0.07
    announce
    0.07
    oon
    0.06
    arin
    0.06
    .BooleanField
    0.06
    ATUS
    0.06
     Ruiz
    0.06
    EGIN
    0.06
     pul
    0.06
    ARAM
    0.06
    Activations Density 0.002%

    No Known Activations