© 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. 23-LLAMASCOPE-RES-32K
    11. 30341
    Prev
    Next
    INDEX
    Explanations

    references to lotteries and winning prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rating
    -0.17
    emoc
    -0.15
    .Usage
    -0.15
     Kun
    -0.14
    rating
    -0.14
    æĢ
    -0.14
    imeo
    -0.14
     rating
    -0.14
     Ratings
    -0.14
    lasses
    -0.14
    POSITIVE LOGITS
     jack
    0.28
     Mega
    0.26
     ticket
    0.25
     jackpot
    0.25
    jack
    0.24
     Jack
    0.24
     scratch
    0.24
     tickets
    0.23
     lottery
    0.22
     Power
    0.22
    Activations Density 0.016%

    No Known Activations