© 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. 9-LLAMASCOPE-RES-131K
    11. 95650
    Prev
    Next
    INDEX
    Explanations

    instances of variable declarations in programming code

    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
    anson
    -0.07
    /MPL
    -0.07
    ston
    -0.07
    arpa
    -0.07
    mlink
    -0.07
    anh
    -0.07
     STDCALL
    -0.06
    anas
    -0.06
    ivec
    -0.06
    ÑĢак
    -0.06
    POSITIVE LOGITS
    IES
    0.08
    ISCO
    0.07
     æ¯
    0.06
    Ctrls
    0.06
    ysz
    0.06
    ÑĢиÑģÑĤи
    0.06
     Nero
    0.06
    оÑĢо
    0.06
    ample
    0.06
    UU
    0.06
    Activations Density 0.004%

    No Known Activations