© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 18105
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to power supply efficiency and circuit design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odia
    -0.16
    umann
    -0.14
     Hayden
    -0.14
    inho
    -0.14
    pron
    -0.13
     ÐłÐ°Ð´Ð¸
    -0.13
    idak
    -0.13
     Wong
    -0.13
     MouseButton
    -0.13
    PropertyChanged
    -0.13
    POSITIVE LOGITS
     rect
    0.30
     buck
    0.29
     DC
    0.28
     supply
    0.28
     Buck
    0.27
     supplies
    0.26
     regulated
    0.26
    supply
    0.24
     AC
    0.24
     dc
    0.24
    Activations Density 0.039%

    No Known Activations