© 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. 18-LLAMASCOPE-RES-32K
    11. 9175
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity and attenuation in signal processing or communication contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çŃ
    -0.15
    _HT
    -0.14
    iom
    -0.14
    angen
    -0.14
     lep
    -0.14
    wan
    -0.14
     phóng
    -0.14
    arch
    -0.14
    _irq
    -0.14
     kin
    -0.14
    POSITIVE LOGITS
     optical
    0.30
     Optical
    0.29
     Fiber
    0.26
     fiber
    0.25
     optics
    0.24
    fiber
    0.24
     lasers
    0.23
     opt
    0.23
     laser
    0.21
     Laser
    0.21
    Activations Density 0.100%

    No Known Activations