© 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. 62097
    Prev
    Next
    INDEX
    Explanations

    collaborative projects and community events

    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
    alue
    -0.07
    -redux
    -0.07
    izontal
    -0.07
    eteor
    -0.07
    orial
    -0.07
    plier
    -0.07
    ÙĦÛĮÙĩ
    -0.07
    ezier
    -0.07
    erer
    -0.07
    oring
    -0.07
    POSITIVE LOGITS
    0.07
     basically
    0.06
    394
    0.06
    108
    0.06
     altern
    0.06
     Ñģобой
    0.06
     consists
    0.06
     consist
    0.06
     gá»ĵm
    0.06
    oor
    0.06
    Activations Density 0.055%

    No Known Activations