© 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. 18465
    Prev
    Next
    INDEX
    Explanations

    references to programming or API-related content

    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
    /jav
    -0.07
    nty
    -0.07
     деÑĢ
    -0.07
    lick
    -0.07
    ruk
    -0.07
    \views
    -0.07
    /compiler
    -0.07
    uong
    -0.07
    еÑĤÑĮ
    -0.07
     showc
    -0.06
    POSITIVE LOGITS
    util
    0.07
    aler
    0.06
     hal
    0.06
     ioutil
    0.06
    EMON
    0.05
     Joyce
    0.05
     accom
    0.05
     Inch
    0.05
    ike
    0.05
     carriers
    0.05
    Activations Density 0.004%

    No Known Activations