© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate methods or approaches to achieving something

    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
    irs
    -0.16
    etsy
    -0.15
    ynn
    -0.14
    iera
    -0.13
    urs
    -0.13
    ycled
    -0.13
    ืà¹ī
    -0.13
    uth
    -0.12
    strained
    -0.12
    ets
    -0.12
    POSITIVE LOGITS
     to
    0.34
     of
    0.30
     forward
    0.30
    ward
    0.28
    finding
    0.26
     for
    0.25
    forward
    0.25
    station
    0.24
    Forward
    0.24
    to
    0.23
    Activations Density 0.035%

    No Known Activations