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. 31-LLAMASCOPE-RES-32K
    6. 1972
    Prev
    Next
    INDEX
    Explanations

    financial terms related to gains and losses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EA
    -0.17
     EA
    -0.17
    OLEAN
    -0.15
     Ea
    -0.15
     Edwards
    -0.15
    DataExchange
    -0.14
     Hyde
    -0.14
    xDA
    -0.14
     Electoral
    -0.14
    inger
    -0.14
    POSITIVE LOGITS
     Soft
    0.40
     Vision
    0.35
    Soft
    0.32
     Son
    0.30
    Vision
    0.29
     Mas
    0.27
    Son
    0.24
    Mas
    0.22
    _SOFT
    0.22
     soft
    0.22
    Activations Density 0.003%

    No Known Activations