© 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. 61116
    Prev
    Next
    INDEX
    Explanations

    references to large data sizes or dimensions in a technical context

    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
    rlen
    -0.08
     èŤ
    -0.07
    iaux
    -0.07
    HAV
    -0.07
    SG
    -0.06
    ibur
    -0.06
    rossover
    -0.06
    ngen
    -0.06
    åĩ¡
    -0.06
    criptors
    -0.06
    POSITIVE LOGITS
    É
    0.07
    ìļĶ
    0.06
     Calvin
    0.06
    YA
    0.06
    ict
    0.06
    yd
    0.06
    &action
    0.06
    768
    0.06
    0.06
     sem
    0.06
    Activations Density 0.000%

    No Known Activations