Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 12876
    Prev
    Next
    INDEX
    Explanations

    significant names and events related to iconic figures and their contributions or occurrences throughout history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'field
    -0.15
    DOMNode
    -0.15
    DDD
    -0.14
    ofday
    -0.14
    _Null
    -0.13
    /topic
    -0.13
    indsight
    -0.13
    getError
    -0.13
    callee
    -0.13
    reopen
    -0.13
    POSITIVE LOGITS
     died
    0.83
     death
    0.73
     dies
    0.72
     dying
    0.65
     deaths
    0.63
     die
    0.60
    æŃ»
    0.60
     Died
    0.59
    death
    0.57
     Death
    0.56
    Activations Density 0.269%

    No Known Activations