© 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. 28059
    Prev
    Next
    INDEX
    Explanations

    references to the generation of random numbers in computing contexts

    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
    ereotype
    -0.14
     bare
    -0.14
    ä¸Ģ级
    -0.13
    jÃŃ
    -0.13
    enza
    -0.13
    اغ
    -0.13
    ä¸ī级
    -0.13
    amus
    -0.13
     deb
    -0.13
     SIL
    -0.13
    POSITIVE LOGITS
     random
    0.66
    random
    0.57
     Random
    0.57
    -random
    0.55
    .random
    0.55
    Random
    0.52
    _random
    0.51
     RANDOM
    0.50
     rand
    0.50
     randomly
    0.48
    Activations Density 0.210%

    No Known Activations