Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95901
    Prev
    Next
    INDEX
    Explanations

    terms related to wireless communication technologies

    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
     Burb
    -0.06
    pios
    -0.06
    ipt
    -0.06
     parade
    -0.06
    osc
    -0.06
    isse
    -0.06
    ãģĺãĤĥãģªãģĦ
    -0.06
    uan
    -0.06
    ply
    -0.06
    usercontent
    -0.06
    POSITIVE LOGITS
    owy
    0.07
    Gap
    0.07
    ovÃŃ
    0.07
    gap
    0.07
     âĢ»
    0.06
    _BOTH
    0.06
    Nested
    0.06
     Nested
    0.06
    ê
    0.06
    HOLDER
    0.06
    Activations Density 0.023%

    No Known Activations