© 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. 15-LLAMASCOPE-RES-131K
    11. 87077
    Prev
    Next
    INDEX
    Explanations

    references to ongoing and long-duration gaming campaigns

    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
    éħį
    -0.07
    apult
    -0.06
    ekler
    -0.05
     orm
    -0.05
     proh
    -0.05
    onga
    -0.05
    iac
    -0.05
     Lear
    -0.05
    azon
    -0.05
    enda
    -0.05
    POSITIVE LOGITS
    ervo
    0.08
    idenav
    0.07
    -Compatible
    0.07
    ypi
    0.07
    ultipart
    0.07
    ForResource
    0.07
    -session
    0.07
     kob
    0.07
    playing
    0.07
     Telecom
    0.07
    Activations Density 0.045%

    No Known Activations