Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93777
    Prev
    Next
    INDEX
    Explanations

    symbols or markup language elements within a text

    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
    pta
    -0.08
    icari
    -0.08
    osu
    -0.07
    икÑĥ
    -0.07
    pter
    -0.06
    лÑĮÑĤ
    -0.06
    ç§ĭ
    -0.06
    ูà¹ī
    -0.06
     treff
    -0.06
    wdx
    -0.06
    POSITIVE LOGITS
    κÏħ
    0.07
    chner
    0.07
    agua
    0.07
    745
    0.07
     hosp
    0.06
    eb
    0.06
    aman
    0.06
    ereo
    0.06
    ¶Į
    0.06
    emin
    0.06
    Activations Density 0.003%

    No Known Activations