© 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. 26-LLAMASCOPE-RES-32K
    11. 1954
    Prev
    Next
    INDEX
    Explanations

    statements or discussions involving relationships and personal actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -0.25
     themselves
    -0.24
    她们
    -0.24
     должно
    -0.17
    Ùģس
    -0.17
     ourselves
    -0.16
    å®ĥ们
    -0.16
    عÙħاÙĦ
    -0.16
     оно
    -0.15
     thems
    -0.15
    POSITIVE LOGITS
     his
    1.37
    his
    1.17
    ä»ĸçļĦ
    1.07
     himself
    0.92
    His
    0.86
     его
    0.84
     zijn
    0.83
     jeho
    0.82
     His
    0.79
     jego
    0.77
    Activations Density 3.119%

    No Known Activations