© 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. 18131
    Prev
    Next
    INDEX
    Explanations

    quantities and descriptions of beverages

    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
    isko
    -0.15
     licensed
    -0.15
    avir
    -0.15
    anio
    -0.14
    arl
    -0.14
    onia
    -0.14
     Licensed
    -0.14
    443
    -0.14
     boxes
    -0.14
    itian
    -0.14
    POSITIVE LOGITS
     glass
    0.63
     Glass
    0.55
    Glass
    0.54
    glass
    0.54
     glasses
    0.48
    çİ»çĴĥ
    0.41
     Glasses
    0.40
     cup
    0.32
    glas
    0.32
     mug
    0.31
    Activations Density 0.048%

    No Known Activations