© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87319
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, particularly those related to scientific or legal contexts

    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
     ev
    -0.06
    /on
    -0.06
    eder
    -0.06
     tit
    -0.06
    buat
    -0.06
     Crab
    -0.06
    wer
    -0.06
     Ferguson
    -0.06
     prow
    -0.05
    869
    -0.05
    POSITIVE LOGITS
    UrlParser
    0.07
    CallCheck
    0.07
    BackingField
    0.07
    OffsetTable
    0.07
    ãĥĥãĥĦ
    0.07
    Intialized
    0.07
    InParameter
    0.07
    erd
    0.07
    .updateDynamic
    0.07
    sein
    0.06
    Activations Density 0.003%

    No Known Activations