© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 24836
    Prev
    Next
    INDEX
    Explanations

    complex terminology and specific references related to evolutionary biology and species classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pul
    -0.14
    кÑĥÑģ
    -0.14
    bour
    -0.14
     native
    -0.14
    doll
    -0.13
     Ryder
    -0.13
     Goodman
    -0.13
    atrix
    -0.13
    vice
    -0.13
     regional
    -0.13
    POSITIVE LOGITS
     Archae
    0.24
     kingdom
    0.23
     unic
    0.23
     Kingdom
    0.22
     cellular
    0.21
     multic
    0.21
     archae
    0.20
     cells
    0.20
    cells
    0.20
     fotos
    0.20
    Activations Density 0.158%

    No Known Activations