© 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. 61847
    Prev
    Next
    INDEX
    Explanations

    references to community events and involvement opportunities

    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
    anzi
    -0.09
    Kids
    -0.08
    ingleton
    -0.08
     kids
    -0.08
    kids
    -0.07
     Kids
    -0.07
    \widgets
    -0.07
    AndView
    -0.07
    õi
    -0.07
    окон
    -0.07
    POSITIVE LOGITS
     adults
    0.20
     adult
    0.19
     Adults
    0.18
    adult
    0.17
    Adult
    0.16
     Adult
    0.16
     grown
    0.14
     adultos
    0.13
     adulte
    0.13
     adulthood
    0.13
    Activations Density 0.076%

    No Known Activations