© 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. 124014
    Prev
    Next
    INDEX
    Explanations

    punctuation and line breaks, indicating article structure or formatting elements

    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
    acci
    -0.08
    erv
    -0.07
    antes
    -0.07
    赤
    -0.07
    >manual
    -0.07
    idas
    -0.07
    illion
    -0.07
    loh
    -0.07
    nid
    -0.07
    rish
    -0.07
    POSITIVE LOGITS
     Alliance
    0.06
    oka
    0.06
     multiple
    0.06
     Cosmos
    0.06
    549
    0.05
     Ranger
    0.05
     Although
    0.05
     tw
    0.05
     Allied
    0.05
    dit
    0.05
    Activations Density 0.020%

    No Known Activations