© 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. 15-LLAMASCOPE-RES-131K
    11. 103729
    Prev
    Next
    INDEX
    Explanations

    coding patterns related to database schema and attributes

    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
    lich
    -0.07
    ven
    -0.07
    æĸ
    -0.07
    ogg
    -0.07
    gain
    -0.06
    .operator
    -0.06
    izio
    -0.06
    948
    -0.06
    fields
    -0.06
    761
    -0.06
    POSITIVE LOGITS
    ÑĪÑĥ
    0.07
    eru
    0.06
    irez
    0.06
    oms
    0.06
    zk
    0.06
     pin
    0.06
    γι
    0.06
    mlin
    0.06
    udu
    0.06
    кÑĥлÑĮ
    0.06
    Activations Density 0.000%

    No Known Activations