© 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. 78236
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequencies

    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
     Cand
    -0.07
     Thurs
    -0.07
    iesel
    -0.07
     Wed
    -0.06
    mons
    -0.06
    sembl
    -0.06
    ihn
    -0.06
     Thu
    -0.06
    azu
    -0.06
    éra
    -0.06
    POSITIVE LOGITS
     Mar
    0.06
    SearchParams
    0.06
    .pix
    0.06
    assis
    0.06
    âĢ«
    0.06
    á»Ĩ
    0.06
    CellStyle
    0.06
    \Collections
    0.06
     Nov
    0.06
     November
    0.06
    Activations Density 0.011%

    No Known Activations