© 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. 76718
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of relation and connections between ideas or subjects

    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
    anka
    -0.07
    женеÑĢ
    -0.07
     horn
    -0.06
     odds
    -0.06
    apper
    -0.06
    ãĥIJãĥ¼
    -0.06
    XL
    -0.06
    afia
    -0.06
    िà¤ķल
    -0.06
    awai
    -0.06
    POSITIVE LOGITS
    ally
    0.07
    /by
    0.07
    usan
    0.07
    croft
    0.07
    ALLY
    0.07
    erdale
    0.07
    isten
    0.06
    ismo
    0.06
    ately
    0.06
    emarks
    0.06
    Activations Density 0.006%

    No Known Activations