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. 10941
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to reactions and species interactions

    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
    /epl
    -0.16
    airy
    -0.16
    /kernel
    -0.15
    械
    -0.14
    taxonomy
    -0.13
    bian
    -0.13
    ardy
    -0.13
    opt
    -0.12
     scala
    -0.12
    locks
    -0.12
    POSITIVE LOGITS
     mole
    0.27
     mo
    0.26
     sto
    0.24
     reaction
    0.23
     equilibrium
    0.23
     react
    0.23
     Reaction
    0.22
     Kb
    0.21
     reacting
    0.20
     reactions
    0.20
    Activations Density 0.010%

    No Known Activations