© 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. 125565
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and related identifiers

    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
     Suspension
    -0.06
    igy
    -0.06
     suspension
    -0.06
    abyrinth
    -0.06
     circ
    -0.06
    ãĥĸãĥª
    -0.06
    Britain
    -0.06
    oso
    -0.05
    á»Ŀ
    -0.05
     wiki
    -0.05
    POSITIVE LOGITS
    PEND
    0.07
    ascus
    0.07
    egral
    0.07
    ìłĪ
    0.07
    ContextHolder
    0.06
    ç²Ĵ
    0.06
     Ø£ØŃ
    0.06
    ioned
    0.06
     listing
    0.06
     ancest
    0.06
    Activations Density 0.000%

    No Known Activations