© 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. 5-LLAMASCOPE-RES-131K
    11. 126039
    Prev
    Next
    INDEX
    Explanations

    terms related to network protocols and diagnostics

    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
    iyat
    -0.09
     Pipe
    -0.07
    uncated
    -0.07
    ivan
    -0.07
    uba
    -0.06
    iter
    -0.06
     Roth
    -0.06
    à¥ģà¤Ĺ
    -0.06
     Jag
    -0.06
    remen
    -0.06
    POSITIVE LOGITS
    cox
    0.07
     Lith
    0.06
    lang
    0.06
    SKTOP
    0.06
    anj
    0.06
    ëŀ«
    0.06
     reserved
    0.06
     آز
    0.06
    .getHeader
    0.06
    886
    0.06
    Activations Density 0.006%

    No Known Activations