© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 104387
    Prev
    Next
    INDEX
    Explanations

    references to events, collaborations, and community engagement

    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
     anymore
    -0.06
     Bri
    -0.06
    (
    -0.06
    asz
    -0.06
    iat
    -0.06
    `
    -0.05
    rag
    -0.05
    USH
    -0.05
     it
    -0.05
     or
    -0.05
    POSITIVE LOGITS
    иÑģÑĤÑĢа
    0.09
    $MESS
    0.08
    §Ãĥ
    0.07
    enza
    0.07
    ;b
    0.07
    NECT
    0.07
    ;element
    0.07
    URLException
    0.07
    åĢį
    0.07
    ahn
    0.07
    Activations Density 0.023%

    No Known Activations