© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70982
    Prev
    Next
    INDEX
    Explanations

    punctuation and other special characters in a structured data format

    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
    eken
    -0.07
    uess
    -0.06
    kr
    -0.06
    lein
    -0.06
     Russ
    -0.06
    izzy
    -0.06
    ï
    -0.06
    pos
    -0.06
     Chapman
    -0.05
    ISM
    -0.05
    POSITIVE LOGITS
     ...(
    0.07
    onta
    0.07
    lea
    0.07
    wall
    0.07
    endent
    0.07
    'util
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.07
    елиÑĩ
    0.07
    esan
    0.06
    otch
    0.06
    Activations Density 0.058%

    No Known Activations