© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 2104
    Prev
    Next
    INDEX
    Explanations

    references to water extraction technologies and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ø¢Ùħ
    -0.14
    udit
    -0.14
     Templ
    -0.14
    è±Ĭ
    -0.13
    åĩ¡
    -0.13
     Imports
    -0.13
     expansion
    -0.12
    ÏĦÏī
    -0.12
    å¯
    -0.12
    EEK
    -0.12
    POSITIVE LOGITS
     technology
    0.32
     prototype
    0.30
     prototypes
    0.29
    technology
    0.29
    prototype
    0.28
     patent
    0.25
     patented
    0.25
     concept
    0.25
     patents
    0.24
     Technology
    0.24
    Activations Density 0.251%

    No Known Activations