© 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. 27-LLAMASCOPE-RES-32K
    11. 6057
    Prev
    Next
    INDEX
    Explanations

    concepts related to frequency and wavelength in technical contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Flow
    -0.15
    Flow
    -0.15
     cast
    -0.15
     punct
    -0.14
     Curl
    -0.14
    vÄĽ
    -0.14
    _FLOW
    -0.14
     gele
    -0.14
     Frost
    -0.14
     transcripts
    -0.14
    POSITIVE LOGITS
     frequency
    0.62
     frequencies
    0.57
     Frequency
    0.55
    frequency
    0.54
     Frequ
    0.54
     freq
    0.54
    Frequency
    0.52
     frequ
    0.49
    .frequency
    0.48
    -frequency
    0.48
    Activations Density 0.168%

    No Known Activations