© 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. 25-LLAMASCOPE-RES-32K
    11. 10976
    Prev
    Next
    INDEX
    Explanations

    text related to food preparation and recipes

    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
    èij
    -0.17
    rese
    -0.16
     sulf
    -0.15
    858
    -0.14
    bia
    -0.14
     chlorine
    -0.14
     buried
    -0.13
    ιδ
    -0.13
     pard
    -0.13
    evi
    -0.13
    POSITIVE LOGITS
     mixture
    0.54
     mix
    0.46
    æ··åIJĪ
    0.34
     Mix
    0.34
    ixture
    0.34
     suspension
    0.33
     mixes
    0.32
    mix
    0.31
     solution
    0.31
     há»Ĺn
    0.30
    Activations Density 0.204%

    No Known Activations