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. 3509
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage

    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
     надо
    -0.08
    _parms
    -0.07
     Called
    -0.07
    abouts
    -0.07
    аÑĪ
    -0.07
    okane
    -0.06
    OTO
    -0.06
    bbe
    -0.06
     called
    -0.06
    TIMER
    -0.06
    POSITIVE LOGITS
    -esque
    0.08
    Furthermore
    0.08
     Furthermore
    0.07
     entirety
    0.07
     ëĺIJíķľ
    0.07
     Throughout
    0.07
    inished
    0.07
     fakat
    0.07
    âĸį
    0.07
     infamous
    0.07
    Activations Density 0.419%

    No Known Activations