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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 25956
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data, particularly financial figures and statistics

    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
     Dwarf
    -0.17
    icus
    -0.16
    pery
    -0.16
     <+
    -0.15
    _traits
    -0.14
    Peter
    -0.14
    400
    -0.14
    70
    -0.14
    Dual
    -0.14
     Dual
    -0.14
    POSITIVE LOGITS
    102
    0.37
    105
    0.36
    106
    0.35
    103
    0.34
    104
    0.31
    101
    0.31
    107
    0.31
    108
    0.30
    109
    0.29
    100
    0.27
    Activations Density 0.064%

    No Known Activations