© 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. 13-LLAMASCOPE-RES-32K
    6. 25108
    Prev
    Next
    INDEX
    Explanations

    references to authority, support, or significant events and concepts related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iface
    -0.15
    codes
    -0.15
    ilog
    -0.15
    ä»ģ
    -0.15
    izzo
    -0.14
    -INF
    -0.14
    asley
    -0.14
    vana
    -0.14
     thus
    -0.14
    utex
    -0.13
    POSITIVE LOGITS
     UserControl
    0.15
    za
    0.15
    etro
    0.14
    éĥİ
    0.14
    (Paint
    0.14
    abin
    0.13
     Perr
    0.13
     diff
    0.13
     Yue
    0.13
    isu
    0.13
    Activations Density 0.011%

    No Known Activations