© 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. 22-LLAMASCOPE-RES-32K
    11. 15998
    Prev
    Next
    INDEX
    Explanations

    variations or forms of the word "wag" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barnett
    -0.17
    еÑģÑĤи
    -0.15
    udad
    -0.15
    .none
    -0.14
    trap
    -0.14
    avou
    -0.14
    chg
    -0.14
    æ®
    -0.14
    ãĥ«ãĥī
    -0.14
    ilk
    -0.13
    POSITIVE LOGITS
    gle
    0.21
     wag
    0.20
    gon
    0.19
    ارش
    0.19
    yu
    0.18
     Kre
    0.16
     vag
    0.16
    tail
    0.15
     tail
    0.15
    nesday
    0.15
    Activations Density 0.010%

    No Known Activations