© 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. 14-LLAMASCOPE-RES-32K
    11. 10150
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to abundance or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eyer
    -0.16
     desper
    -0.15
     Vest
    -0.14
     synonyms
    -0.14
    cov
    -0.14
    indow
    -0.13
     zig
    -0.13
    rlen
    -0.13
    /component
    -0.13
    moz
    -0.13
    POSITIVE LOGITS
    agg
    0.19
    rede
    0.15
    377
    0.15
    abox
    0.15
    ิà¸į
    0.14
    жи
    0.14
    924
    0.14
    pearance
    0.14
    Ticks
    0.14
    bfd
    0.14
    Activations Density 0.034%

    No Known Activations