© 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. 17-LLAMASCOPE-RES-131K
    11. 72734
    Prev
    Next
    INDEX
    Explanations

    code snippets indicating method definitions and return statements in programming languages

    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
     equ
    -0.06
    .Forms
    -0.06
     McConnell
    -0.06
    odd
    -0.06
    ph
    -0.06
    -0.05
     dual
    -0.05
    orian
    -0.05
     NC
    -0.05
    оÑĪ
    -0.05
    POSITIVE LOGITS
    umd
    0.07
    abei
    0.07
    ahlen
    0.07
     mastur
    0.07
    Wire
    0.07
    uncture
    0.07
    åĽº
    0.07
    irector
    0.07
    _wire
    0.06
    disposed
    0.06
    Activations Density 0.002%

    No Known Activations