© 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. 98149
    Prev
    Next
    INDEX
    Explanations

    references to information and suggestions

    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
    eh
    -0.06
    inki
    -0.06
     own
    -0.06
     hob
    -0.06
     meaning
    -0.06
    .prototype
    -0.06
     with
    -0.06
    wise
    -0.06
     states
    -0.06
    normal
    -0.06
    POSITIVE LOGITS
    /tiny
    0.08
     Porno
    0.07
    idar
    0.07
    washer
    0.07
    alat
    0.07
     SpringApplication
    0.07
    기ì¤Ģ
    0.07
    CString
    0.07
    .navigator
    0.07
    .LookAndFeel
    0.07
    Activations Density 0.006%

    No Known Activations