© 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. 126779
    Prev
    Next
    INDEX
    Explanations

    references to sponsorship and marketing opportunities

    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
     aras
    -0.08
    ãģŁãĤī
    -0.07
    aida
    -0.06
    LY
    -0.06
    enu
    -0.06
    ãĤ¦ãĥĪ
    -0.06
    stood
    -0.06
    096
    -0.06
    clock
    -0.06
    BY
    -0.06
    POSITIVE LOGITS
     your
    0.09
     yourself
    0.09
    ä½łçļĦ
    0.08
    ÑĢей
    0.07
    ingu
    0.07
    ongan
    0.07
    ÂŃing
    0.07
    zie
    0.07
     Yourself
    0.07
    iang
    0.07
    Activations Density 0.098%

    No Known Activations