Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 25965
    Prev
    Next
    INDEX
    Explanations

    the presence of shared knowledge and expertise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    аÑĤа
    -0.14
    leme
    -0.14
    upil
    -0.13
    arkin
    -0.13
    çķĮ
    -0.13
    ìľ¡
    -0.13
    urgy
    -0.12
    vironments
    -0.12
    аÑĤÑĥ
    -0.12
    892
    -0.12
    POSITIVE LOGITS
     knowledge
    0.86
    knowledge
    0.75
     Knowledge
    0.72
    Knowledge
    0.66
    çŁ¥è¯Ĩ
    0.59
     KNOW
    0.48
     understanding
    0.47
     conosc
    0.42
    nowledge
    0.41
     know
    0.41
    Activations Density 0.230%

    No Known Activations