© 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. 24-LLAMASCOPE-RES-32K
    11. 14153
    Prev
    Next
    INDEX
    Explanations

    mentions of "hour" and "hours," especially in the context of time allocations or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AZY
    -0.19
    ively
    -0.17
    ardy
    -0.16
    ese
    -0.16
    laÅŁtır
    -0.15
    elden
    -0.15
    kara
    -0.15
    pery
    -0.15
    ember
    -0.15
    opper
    -0.14
    POSITIVE LOGITS
    -long
    0.34
    glass
    0.29
    long
    0.28
    /day
    0.23
     spent
    0.22
    izont
    0.18
    lies
    0.18
    :min
    0.18
    /d
    0.17
    ouble
    0.17
    Activations Density 0.035%

    No Known Activations