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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5284
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that may indicate sentence endings or structural elements in a document

    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
    .epam
    -0.06
    âm
    -0.06
    offline
    -0.06
    oze
    -0.06
    enie
    -0.06
    PD
    -0.06
    cripts
    -0.06
     Bend
    -0.06
     hos
    -0.06
     Dram
    -0.05
    POSITIVE LOGITS
    rire
    0.07
    çĨĬ
    0.07
    raquo
    0.07
    nummer
    0.06
     tá»
    0.06
    à¸Ńำ
    0.06
    uiltin
    0.06
    ivic
    0.06
    abbo
    0.06
    аж
    0.06
    Activations Density 0.005%

    No Known Activations