© 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. 118413
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or amounts

    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
    817
    -0.09
    ì·¨
    -0.07
    ATCH
    -0.06
    strncmp
    -0.06
    ä¸ĢäºĽ
    -0.06
    694
    -0.06
    íĹĮ
    -0.06
    opensource
    -0.06
     ones
    -0.06
    .ci
    -0.06
    POSITIVE LOGITS
    å·¦åı³
    0.08
     assorted
    0.07
     finest
    0.07
    .Apis
    0.06
    auth
    0.06
     Quy
    0.06
     Lage
    0.06
    sworth
    0.06
    andi
    0.06
    abyte
    0.06
    Activations Density 0.018%

    No Known Activations