© 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. 16841
    Prev
    Next
    INDEX
    Explanations

    terms related to waste management and recycling processes

    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
    SHA
    -0.06
     phantom
    -0.06
    owan
    -0.06
    anz
    -0.06
    ÑģпÑĸлÑĮ
    -0.06
    VICE
    -0.06
    ord
    -0.05
    itas
    -0.05
    ç¯ĩ
    -0.05
     huz
    -0.05
    POSITIVE LOGITS
     separation
    0.10
     Separ
    0.10
     separated
    0.09
     separ
    0.09
    Separated
    0.08
     separating
    0.08
    Separ
    0.08
    -separated
    0.08
     separates
    0.08
    oola
    0.08
    Activations Density 0.022%

    No Known Activations