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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 44161
    Prev
    Next
    INDEX
    Explanations

    formatting elements often used in mathematical or scientific documents

    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
    iaux
    -0.06
     the
    -0.06
    ely
    -0.06
     Simpson
    -0.06
     Dir
    -0.06
    issance
    -0.06
     Gor
    -0.05
     RE
    -0.05
     ``
    -0.05
    ı
    -0.05
    POSITIVE LOGITS
    rule
    0.15
    line
    0.11
    phant
    0.10
    sep
    0.10
    fill
    0.10
    bottom
    0.09
    align
    0.09
    row
    0.09
    Rule
    0.09
    rules
    0.09
    Activations Density 0.013%

    No Known Activations