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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-LLAMASCOPE-RES-32K
    6. 30577
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific theories and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osome
    -0.15
    аж
    -0.14
    ansa
    -0.14
    uru
    -0.13
    uden
    -0.13
    atcher
    -0.13
    ãģĦãĤĦ
    -0.13
    osomes
    -0.13
    venes
    -0.13
    ÑĪка
    -0.13
    POSITIVE LOGITS
     produce
    0.45
     produces
    0.44
     producing
    0.41
     resulting
    0.38
    produce
    0.35
     Produ
    0.35
     resulted
    0.35
     result
    0.33
     Produce
    0.32
    result
    0.31
    Activations Density 0.275%

    No Known Activations