© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 846
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and player statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustos
    -0.16
    esti
    -0.16
    èµ¢
    -0.15
    abar
    -0.15
    ÑĸÑħ
    -0.14
    utura
    -0.14
    984
    -0.13
    âl
    -0.13
    LBL
    -0.13
    -medium
    -0.13
    POSITIVE LOGITS
     production
    0.22
     stat
    0.20
     Production
    0.19
    production
    0.18
     productivity
    0.18
    Production
    0.18
    -production
    0.18
     fantasy
    0.18
     leadership
    0.17
     lights
    0.17
    Activations Density 0.082%

    No Known Activations