© 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. 17353
    Prev
    Next
    INDEX
    Explanations

    specific programming or technical terms related to software development

    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
    *</
    -0.09
    ongan
    -0.08
     öden
    -0.08
    lsru
    -0.08
    ÚĨار
    -0.07
    iali
    -0.07
    _REPLACE
    -0.07
    ---</
    -0.07
    ÄIJT
    -0.07
     bát
    -0.07
    POSITIVE LOGITS
     Lorem
    0.06
     شع
    0.05
    'S
    0.05
     notwithstanding
    0.05
     ~
    0.05
     Liber
    0.05
    ãĥ¼ãĥĸ
    0.05
     convenience
    0.05
    igh
    0.05
     Nathan
    0.05
    Activations Density 0.026%

    No Known Activations