© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55499
    Prev
    Next
    INDEX
    Explanations

    references to data formats and structure in code related to volume handling and SQLite integration

    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
     slopes
    -0.06
     premise
    -0.06
     Frank
    -0.06
     rack
    -0.05
     pare
    -0.05
     Syn
    -0.05
    _invoke
    -0.05
     syn
    -0.05
     hormones
    -0.05
    Html
    -0.05
    POSITIVE LOGITS
    .gdx
    0.09
     Reader
    0.08
    _rw
    0.08
     reader
    0.08
    iona
    0.08
    io
    0.08
    reopen
    0.08
    IO
    0.08
    asio
    0.07
    Ùħز
    0.07
    Activations Density 0.012%

    No Known Activations