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. 29264
    Prev
    Next
    INDEX
    Explanations

    formatting or style-related elements in coding or markup languages

    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
    ç¦
    -0.06
    umn
    -0.06
    ology
    -0.06
    ikon
    -0.06
    went
    -0.06
    Ñĩний
    -0.06
    üst
    -0.06
    ellation
    -0.06
    ÅĻeb
    -0.05
    ins
    -0.05
    POSITIVE LOGITS
    ://
    0.07
    ECT
    0.06
    .locals
    0.06
    atest
    0.06
    ÑıÑģ
    0.06
    à¸Ļม
    0.06
     Bren
    0.06
    outes
    0.06
    ogany
    0.06
     Dun
    0.06
    Activations Density 0.000%

    No Known Activations