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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98849
    Prev
    Next
    INDEX
    Explanations

    references to daily news publications or reports

    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
    noop
    -0.06
    ersh
    -0.06
    erland
    -0.06
     rod
    -0.06
    arine
    -0.06
    olute
    -0.06
    Ñıж
    -0.06
     Rat
    -0.06
    aturated
    -0.06
     uintptr
    -0.06
    POSITIVE LOGITS
    (example
    0.07
    _Font
    0.06
     PureComponent
    0.06
    ihil
    0.06
    ção
    0.06
     VÅ¡ech
    0.06
    üstü
    0.06
    cz
    0.06
    593
    0.06
    iona
    0.06
    Activations Density 0.013%

    No Known Activations