© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10662
    Prev
    Next
    INDEX
    Explanations

    processes related to membership, applications, and participant interactions

    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
     your
    -0.28
     yourself
    -0.23
    your
    -0.20
    ä½łçļĦ
    -0.19
    Your
    -0.17
    ulo
    -0.17
     Your
    -0.17
     votre
    -0.17
    uci
    -0.16
    umper
    -0.16
    POSITIVE LOGITS
    ayi
    0.20
     themselves
    0.18
    RNA
    0.16
    اÙĨÛĮ
    0.15
    idy
    0.14
    ãģ£ãģ¡
    0.14
    PHY
    0.14
    ryan
    0.14
    itten
    0.14
     globalization
    0.14
    Activations Density 0.443%

    No Known Activations