© 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. 40193
    Prev
    Next
    INDEX
    Explanations

    terms related to structural and systemic attributes in various contexts

    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
     Emit
    -0.07
    uck
    -0.07
    à¸Ńว
    -0.06
    eya
    -0.06
     alternate
    -0.06
    ÏģÏį
    -0.06
    819
    -0.06
    otos
    -0.06
    ाश
    -0.06
    оÑĨÑĸ
    -0.06
    POSITIVE LOGITS
     rather
    0.09
    rather
    0.08
     ones
    0.08
    ones
    0.08
     nature
    0.07
     Rather
    0.07
    ãĤĤãģ®
    0.07
     affair
    0.07
     meaning
    0.07
    /static
    0.07
    Activations Density 0.058%

    No Known Activations