© 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. 25-LLAMASCOPE-RES-32K
    11. 10424
    Prev
    Next
    INDEX
    Explanations

    references to updates or changes in technology-related services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocache
    -0.15
    oux
    -0.15
    redis
    -0.14
    à¸Ļาม
    -0.14
    ialized
    -0.14
    undry
    -0.14
     addCriterion
    -0.13
     recru
    -0.13
    áÅĻ
    -0.13
    SGlobal
    -0.13
    POSITIVE LOGITS
     transition
    0.69
    transition
    0.62
     Transition
    0.61
     migration
    0.59
    Transition
    0.57
     switch
    0.56
    -transition
    0.54
     transitions
    0.52
     Switch
    0.52
     Migration
    0.51
    Activations Density 0.190%

    No Known Activations