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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 5605
    Prev
    Next
    INDEX
    Explanations

    references to kidney transplants and related medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metav
    -0.15
    ipop
    -0.14
     ar
    -0.14
     Huffman
    -0.14
     bru
    -0.14
    oq
    -0.14
    bz
    -0.14
     pro
    -0.14
    sterol
    -0.14
     hern
    -0.14
    POSITIVE LOGITS
     graft
    0.26
     transplant
    0.26
     recipients
    0.25
     rejection
    0.25
     recipient
    0.25
    gra
    0.23
     transplantation
    0.23
     rejecting
    0.23
    recipient
    0.22
     organ
    0.22
    Activations Density 0.009%

    No Known Activations