© 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. 81122
    Prev
    Next
    INDEX
    Explanations

    instructions related to downloading images or files

    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
    linger
    -0.07
    enz
    -0.07
    abi
    -0.07
    ãģłãģª
    -0.07
    essel
    -0.06
    cps
    -0.06
    970
    -0.06
    uchs
    -0.06
    cela
    -0.06
     Vid
    -0.06
    POSITIVE LOGITS
     getSource
    0.07
    adlo
    0.07
    lop
    0.06
    /target
    0.06
    505
    0.06
    edium
    0.06
     gön
    0.06
    GA
    0.06
    eryl
    0.06
    hang
    0.05
    Activations Density 0.001%

    No Known Activations