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. 4-LLAMASCOPE-RES-32K
    6. 26642
    Prev
    Next
    INDEX
    Explanations

    terms related to COVID-19 variants and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anter
    -0.16
     Meredith
    -0.15
    ìĬ
    -0.14
    .SDK
    -0.14
    æ´
    -0.14
    ooke
    -0.14
     defaultMessage
    -0.14
    ekyll
    -0.14
    woke
    -0.14
     tô
    -0.14
    POSITIVE LOGITS
    éĴ
    0.15
     奥
    0.14
    hiro
    0.14
     Ngá»įc
    0.14
    åłĤ
    0.14
    241
    0.13
    _IRQ
    0.13
    igue
    0.13
    ávka
    0.13
     discount
    0.13
    Activations Density 0.194%

    No Known Activations