© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    content related to fundraising efforts and charitable donations

    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
     Kun
    -0.17
     accord
    -0.14
    loat
    -0.14
    Rated
    -0.14
     minority
    -0.14
    layan
    -0.13
    _fifo
    -0.13
     Discounts
    -0.13
     Satisfaction
    -0.13
    isd
    -0.13
    POSITIVE LOGITS
     fundraising
    0.33
     fund
    0.31
    åĭŁ
    0.29
     Fund
    0.29
     fundraiser
    0.28
     fundra
    0.27
     raising
    0.27
     raised
    0.26
     Raised
    0.26
     collections
    0.25
    Activations Density 0.112%

    No Known Activations