© 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. 15-LLAMASCOPE-RES-131K
    11. 61846
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to data structure manipulation

    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
     temper
    -0.06
    igung
    -0.06
     compress
    -0.06
    mour
    -0.06
    ÏģίοÏħ
    -0.05
     Buffer
    -0.05
     Ske
    -0.05
     Hazel
    -0.05
    IPH
    -0.05
     buffer
    -0.05
    POSITIVE LOGITS
    uede
    0.07
    *sizeof
    0.07
    RAINT
    0.07
    IZER
    0.07
    rons
    0.06
    umps
    0.06
    iser
    0.06
    .esp
    0.06
    eba
    0.06
    elle
    0.06
    Activations Density 0.019%

    No Known Activations