© 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. 83065
    Prev
    Next
    INDEX
    Explanations

    programming keywords and structures related to arrays, objects, and functions

    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
    جÙĪ
    -0.07
    pis
    -0.06
    ldr
    -0.06
    ROID
    -0.06
    λλη
    -0.06
    ovi
    -0.06
    aille
    -0.06
    ijken
    -0.06
    cela
    -0.06
    igli
    -0.06
    POSITIVE LOGITS
    rup
    0.07
    utar
    0.06
    ioned
    0.06
     +
    0.06
    ductive
    0.06
    ingham
    0.06
    SV
    0.06
     ÃĹ
    0.06
    anske
    0.06
    chal
    0.06
    Activations Density 0.120%

    No Known Activations