© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31426
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing guidance and making recommendations

    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
     for
    -0.28
     длÑı
    -0.21
     untuk
    -0.20
     για
    -0.20
    	for
    -0.19
     pentru
    -0.18
     für
    -0.17
    alu
    -0.17
     voor
    -0.17
    为
    -0.17
    POSITIVE LOGITS
     purposes
    0.82
     sake
    0.81
     purpose
    0.42
     reasons
    0.41
     PURPOSE
    0.35
    purpose
    0.33
     reason
    0.30
    Purpose
    0.30
    pur
    0.30
    æĿ¥è¯´
    0.29
    Activations Density 0.705%

    No Known Activations