© 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. 4-LLAMASCOPE-RES-32K
    11. 25728
    Prev
    Next
    INDEX
    Explanations

    names of influential historical figures and their associated dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inf
    -0.16
     Psychic
    -0.15
    /licenses
    -0.14
    orda
    -0.14
    irsch
    -0.14
    ibe
    -0.14
    &&!
    -0.14
     sen
    -0.14
    ãĥ¼ãĥ«ãĥī
    -0.13
    erte
    -0.13
    POSITIVE LOGITS
    ofire
    0.17
    aggi
    0.14
    indir
    0.14
    ché
    0.14
    ystack
    0.14
     Factory
    0.13
    BUF
    0.13
    нÑı
    0.13
    ASCADE
    0.13
    anno
    0.13
    Activations Density 0.017%

    No Known Activations