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. 23-LLAMASCOPE-RES-32K
    6. 914
    Prev
    Next
    INDEX
    Explanations

    discussions and indicators of economic changes and trends over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    week
    -0.25
    -week
    -0.23
    weeks
    -0.23
     Weeks
    -0.23
    Week
    -0.23
     week
    -0.20
     Week
    -0.20
    /month
    -0.20
     fortn
    -0.19
    _week
    -0.19
    POSITIVE LOGITS
    ä¸īå¹´
    0.60
     years
    0.58
     Years
    0.50
    Years
    0.46
    years
    0.46
     five
    0.45
     YEARS
    0.43
     Jahre
    0.39
    _years
    0.39
     year
    0.38
    Activations Density 0.432%

    No Known Activations