© 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. 31-LLAMASCOPE-RES-32K
    11. 13896
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with changes over time

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     åħĪ
    -0.15
    æĹ©
    -0.14
     preced
    -0.14
     predecess
    -0.14
    -prepend
    -0.13
    inand
    -0.13
    itles
    -0.13
    лÑĭÑħ
    -0.13
    odelist
    -0.12
    iloc
    -0.12
    POSITIVE LOGITS
     afterward
    0.99
     afterwards
    0.99
     thereafter
    0.97
     Afterwards
    0.75
     subsequently
    0.74
     later
    0.63
     subsequent
    0.56
    ä¹ĭåIJİ
    0.56
    later
    0.53
    Later
    0.49
    Activations Density 0.515%

    No Known Activations