© 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. 40646
    Prev
    Next
    INDEX
    Explanations

    references to navigation or interaction within a website or online form

    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
    rees
    -0.07
    _ED
    -0.07
    éal
    -0.06
    -IS
    -0.06
     prom
    -0.06
    emy
    -0.06
    никÑĸв
    -0.06
    nes
    -0.06
     mines
    -0.06
     NDEBUG
    -0.06
    POSITIVE LOGITS
    sitemap
    0.07
    404
    0.07
    è¶ħ
    0.07
    ura
    0.06
     omas
    0.06
    ziel
    0.06
     either
    0.06
     setContent
    0.06
    490
    0.06
    ouro
    0.06
    Activations Density 0.004%

    No Known Activations