© 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 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. 17-LLAMASCOPE-RES-131K
    11. 130248
    Prev
    Next
    INDEX
    Explanations

    phrases that address or refer to the reader directly, particularly about user experience and recommendations

    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
     Huffman
    -0.07
    STA
    -0.07
    оваÑĢ
    -0.07
    æ¾
    -0.07
    ictionary
    -0.06
    vg
    -0.06
    uft
    -0.06
     anomaly
    -0.06
    .inst
    -0.06
    ector
    -0.06
    POSITIVE LOGITS
     missed
    0.07
    ooter
    0.07
     Mes
    0.06
     wait
    0.06
     waiting
    0.06
    bard
    0.06
     waited
    0.06
    miss
    0.06
     기ëĭ¤
    0.06
     fol
    0.05
    Activations Density 0.016%

    No Known Activations