© 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. 89133
    Prev
    Next
    INDEX
    Explanations

    content related to previews and predictions

    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
    á»įc
    -0.06
    imientos
    -0.06
    /non
    -0.06
    æĬ½
    -0.06
     Roc
    -0.06
    ik
    -0.05
    (EXPR
    -0.05
     Juda
    -0.05
    indi
    -0.05
    ãĥ«ãĥķ
    -0.05
    POSITIVE LOGITS
    894
    0.09
    699
    0.07
    899
    0.07
    906
    0.07
    ussion
    0.07
    ragment
    0.07
    ä¸Ģä¸ĭ
    0.06
    ÑĪка
    0.06
    allax
    0.06
    akash
    0.06
    Activations Density 0.011%

    No Known Activations