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. 30897
    Prev
    Next
    INDEX
    Explanations

    references to significant literary works and their authors

    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
     Euler
    -0.16
     Agricult
    -0.14
     Zimbabwe
    -0.14
     euler
    -0.14
    Forge
    -0.14
    ocab
    -0.13
     Raptors
    -0.13
     Airbus
    -0.13
     Mp
    -0.13
    hest
    -0.13
    POSITIVE LOGITS
     Gins
    0.43
     Beat
    0.36
     Beats
    0.36
     Bur
    0.35
     Ker
    0.34
     Allen
    0.31
    Beat
    0.31
     beat
    0.30
     beats
    0.27
    Bur
    0.27
    Activations Density 0.025%

    No Known Activations