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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56033
    Prev
    Next
    INDEX
    Explanations

    references to ranges or comparisons involving quantities and percentages

    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
    á»IJ
    -0.09
    reste
    -0.07
    uf
    -0.07
    luet
    -0.07
    FromClass
    -0.07
    zon
    -0.07
    üçük
    -0.07
    ones
    -0.07
    Lifecycle
    -0.07
    üf
    -0.06
    POSITIVE LOGITS
    iator
    0.07
    ä»ĭ
    0.07
    VG
    0.06
    oland
    0.06
    jec
    0.06
     sexes
    0.06
     zero
    0.06
    ted
    0.06
    биÑĤ
    0.05
     two
    0.05
    Activations Density 0.007%

    No Known Activations