© 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. 25-LLAMASCOPE-RES-32K
    11. 23459
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its context within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -0.19
     Mondays
    -0.18
     Thurs
    -0.18
     Fridays
    -0.17
     Tomorrow
    -0.17
     Tues
    -0.17
     Saturdays
    -0.16
     friday
    -0.16
    Wednesday
    -0.15
    Fri
    -0.15
    POSITIVE LOGITS
     late
    0.90
    late
    0.71
     Late
    0.64
     early
    0.60
    Late
    0.60
    early
    0.49
     mid
    0.49
     spring
    0.37
     Early
    0.36
     fall
    0.35
    Activations Density 0.186%

    No Known Activations