© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83307
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and elements, particularly in a coding context

    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
     ÙħÙĪÙĦ
    -0.06
    avia
    -0.06
    ennie
    -0.06
    iston
    -0.06
    ÑĤÑİ
    -0.06
    ·¸
    -0.06
     urn
    -0.06
    TOTYPE
    -0.06
    Otherwise
    -0.05
     otherwise
    -0.05
    POSITIVE LOGITS
    either
    0.07
     either
    0.07
    egov
    0.07
     Either
    0.07
    ither
    0.07
    åıĬåħ¶
    0.06
     varargin
    0.06
    illard
    0.06
    Either
    0.06
     Raz
    0.06
    Activations Density 0.020%

    No Known Activations