© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107290
    Prev
    Next
    INDEX
    Explanations

    references to web development technologies, particularly HTML, JavaScript, and CSS

    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
    exampleInput
    -0.08
    êt
    -0.08
    /../
    -0.07
    ãģķãĤĵ
    -0.07
    slashes
    -0.07
     nomine
    -0.07
    OperationException
    -0.07
    _MACRO
    -0.06
    LATED
    -0.06
     Fade
    -0.06
    POSITIVE LOGITS
    rick
    0.07
    5
    0.07
    rant
    0.07
    wan
    0.06
    Native
    0.06
     molec
    0.06
     native
    0.06
    uzzi
    0.06
    itag
    0.06
    undi
    0.06
    Activations Density 0.007%

    No Known Activations