© 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. 30-LLAMASCOPE-RES-32K
    11. 28186
    Prev
    Next
    INDEX
    Explanations

    variations of the word "nest" and its derivatives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    arsity
    -0.15
    uels
    -0.15
    æĻ´
    -0.15
    ahlen
    -0.14
    è¿·
    -0.14
    rror
    -0.14
    aily
    -0.14
    mpar
    -0.14
    Ø°
    -0.14
    ÂŃn
    -0.14
    POSITIVE LOGITS
    lé
    0.35
    led
    0.29
    le
    0.28
    ea
    0.26
    ling
    0.26
    orian
    0.24
    eg
    0.22
    ucc
    0.22
     Egg
    0.21
    egg
    0.21
    Activations Density 0.006%

    No Known Activations