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. 11465
    Prev
    Next
    INDEX
    Explanations

    symbols and characters related to mathematical or scientific notation

    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
     POLIT
    -0.07
    ellery
    -0.06
    taboola
    -0.06
    ãĥ³ãĤ¯
    -0.06
     Repair
    -0.06
     Auswahl
    -0.06
    annes
    -0.06
    .modules
    -0.06
    ovsky
    -0.06
     hackers
    -0.06
    POSITIVE LOGITS
     buffering
    0.09
     applicant
    0.08
     traffic
    0.08
     density
    0.08
    applicant
    0.08
     buffers
    0.08
    Density
    0.07
     Storm
    0.07
     ingress
    0.07
     Traffic
    0.07
    Activations Density 0.006%

    No Known Activations