© 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. 13983
    Prev
    Next
    INDEX
    Explanations

    key terms related to endangered species and their conservation

    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
    wdx
    -0.12
    IIIK
    -0.12
    TRGL
    -0.12
    UniformLocation
    -0.12
    xEE
    -0.12
    xDD
    -0.12
    .opendaylight
    -0.12
    xdc
    -0.12
    .ImageView
    -0.12
    @nate
    -0.12
    POSITIVE LOGITS
     Geb
    0.57
     McB
    0.54
     Hob
    0.54
     EB
    0.53
     Cobb
    0.52
     Jeb
    0.52
     Eb
    0.51
     Cob
    0.50
     XB
    0.50
     Kob
    0.50
    Activations Density 1.402%

    No Known Activations