© 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. 18-LLAMASCOPE-RES-32K
    11. 27150
    Prev
    Next
    INDEX
    Explanations

    locations and venues for community events

    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
     infr
    -0.16
    $MESS
    -0.15
    dens
    -0.15
    çĤİ
    -0.14
    ses
    -0.14
     éĢģ
    -0.14
    inton
    -0.14
     æĸ¼
    -0.14
    aci
    -0.13
     phys
    -0.13
    POSITIVE LOGITS
     complex
    0.15
    atcher
    0.15
    complex
    0.15
     Complex
    0.15
    æĶ
    0.14
     located
    0.14
     adjunct
    0.14
    Complex
    0.14
    iman
    0.14
    εÏĦ
    0.14
    Activations Density 0.083%

    No Known Activations