© 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. 9-LLAMASCOPE-RES-32K
    11. 10032
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or relationships between entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ¹Ħ
    -0.16
    ourcem
    -0.15
     ent
    -0.14
     anc
    -0.14
     coc
    -0.13
    ercul
    -0.13
     Cel
    -0.13
    .getConnection
    -0.13
     Rub
    -0.13
     crab
    -0.13
    POSITIVE LOGITS
    etik
    0.16
    ummer
    0.16
    erli
    0.15
    onaut
    0.14
    ingly
    0.14
    acom
    0.14
    andler
    0.14
    698
    0.14
    PFN
    0.14
     вклад
    0.13
    Activations Density 0.799%

    No Known Activations