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. 125745
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and certain contextual cues in written content

    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
    acco
    -0.06
     سابÙĤ
    -0.06
    rez
    -0.06
    .apple
    -0.06
     vice
    -0.06
     ARTICLE
    -0.06
    çĴ
    -0.06
    ãģ©ãģĵ
    -0.06
    abb
    -0.05
    ÑĥÑĢÑģ
    -0.05
    POSITIVE LOGITS
    ForResource
    0.07
     عشر
    0.06
    /Foundation
    0.06
    Reload
    0.06
    isphere
    0.06
    åı·
    0.06
    iline
    0.06
    utos
    0.06
    uem
    0.06
    ì§ľ
    0.06
    Activations Density 0.074%

    No Known Activations