© 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. 31-LLAMASCOPE-RES-32K
    11. 5813
    Prev
    Next
    INDEX
    Explanations

    references to dates, locations, and events in a financial or economic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :http
    -0.13
    plusplus
    -0.13
    OKIE
    -0.13
    occo
    -0.13
    emachine
    -0.13
    CEEDED
    -0.12
    åĴĮ
    -0.12
    *↵↵
    -0.12
    SCII
    -0.12
    ewe
    -0.12
    POSITIVE LOGITS
     REUTERS
    0.25
    (Photo
    0.25
    .AP
    0.25
    (AP
    0.24
     photographed
    0.23
     Photo
    0.23
     photo
    0.22
    Photo
    0.21
     file
    0.21
    .Photo
    0.21
    Activations Density 0.035%

    No Known Activations