© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128650
    Prev
    Next
    INDEX
    Explanations

    references to authors and publications in scientific research

    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
    cken
    -0.08
     lParam
    -0.07
    cke
    -0.06
    Ļ
    -0.06
    erot
    -0.06
    ãĤ¹ãĥ¬
    -0.06
    iones
    -0.06
     göl
    -0.06
    umas
    -0.06
    REET
    -0.06
    POSITIVE LOGITS
    adder
    0.06
     Hir
    0.06
     Ner
    0.06
    drv
    0.06
    edException
    0.06
     petroleum
    0.06
     alarm
    0.06
    iteur
    0.06
     Dou
    0.05
     pitch
    0.05
    Activations Density 0.001%

    No Known Activations