© 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. 106384
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns in code or data 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
    acher
    -0.08
    ẩm
    -0.07
    oca
    -0.07
    ycin
    -0.07
    asar
    -0.07
    414
    -0.07
    озна
    -0.07
    azar
    -0.06
     suffix
    -0.06
    448
    -0.06
    POSITIVE LOGITS
    allo
    0.06
    ãĥķãĤ
    0.06
     سب
    0.06
    Ĥ¹
    0.06
     mát
    0.06
    ãĥªãĤ«
    0.06
     Mega
    0.06
    PIC
    0.06
     Newest
    0.05
    Ģìŀ¥
    0.05
    Activations Density 0.002%

    No Known Activations