© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 9183
    Prev
    Next
    INDEX
    Explanations

    terms related to incentives and incentive-based programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ern
    -0.17
    iska
    -0.16
    ake
    -0.16
    ish
    -0.16
    ills
    -0.15
    auer
    -0.15
    CASE
    -0.15
    è¬
    -0.15
    Ø©
    -0.15
    ar
    -0.15
    POSITIVE LOGITS
    /response
    0.17
    /prom
    0.16
    æĿIJ
    0.16
    oeff
    0.15
    ÑģÑĮ
    0.15
    물ìĿĦ
    0.15
    -response
    0.15
    eyle
    0.14
    mpar
    0.14
    stype
    0.14
    Activations Density 0.038%

    No Known Activations