© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 32071
    Prev
    Next
    INDEX
    Explanations

    references to Jewish history and its representation in narratives

    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
    iran
    -0.16
    IDS
    -0.16
    ymoon
    -0.15
    ecta
    -0.14
     Kos
    -0.14
    avanaugh
    -0.14
     Roc
    -0.14
     Buddy
    -0.14
    /cop
    -0.14
    umar
    -0.14
    POSITIVE LOGITS
     Mandatory
    0.34
     Mand
    0.30
     British
    0.26
     mandate
    0.24
     Palestine
    0.23
     mandatory
    0.23
     Partition
    0.22
     Brit
    0.22
     Hist
    0.21
     Palm
    0.21
    Activations Density 0.034%

    No Known Activations