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. 126662
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    /*č↵
    -0.07
    Duplicates
    -0.07
    adors
    -0.07
    onica
    -0.07
    mobx
    -0.07
    ë²Į
    -0.07
    DefaultValue
    -0.07
    deniz
    -0.06
    .unit
    -0.06
    ارات
    -0.06
    POSITIVE LOGITS
    \Bundle
    0.06
    conc
    0.06
     viagra
    0.06
    WidgetItem
    0.06
     Conc
    0.06
    ãĥªãĤ¹
    0.05
     McMahon
    0.05
    agh
    0.05
     hass
    0.05
    /
    0.05
    Activations Density 0.000%

    No Known Activations