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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 21622
    Prev
    Next
    INDEX
    Explanations

    the repeated mention of "mach" with varying numerical values associated with it, indicating a focus on instances related to "mach" as a key concept or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dime
    -0.15
     Diy
    -0.15
    klä
    -0.15
    oggler
    -0.15
    ILog
    -0.14
    ós
    -0.14
    zens
    -0.14
    leyen
    -0.14
    askets
    -0.14
    ctions
    -0.14
    POSITIVE LOGITS
    inations
    0.24
    ismo
    0.22
    anical
    0.21
    inery
    0.20
    etes
    0.18
    hap
    0.18
    intosh
    0.18
     mach
    0.18
     Mach
    0.17
    ete
    0.17
    Activations Density 0.004%

    No Known Activations