Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 18077
    Prev
    Next
    INDEX
    Explanations

    instances of the word "abuse" 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 @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æı
    -0.15
    оби
    -0.14
    uture
    -0.14
    iliz
    -0.14
    ãĤ·ãĤ¢
    -0.13
    تاÙĨ
    -0.13
    ari
    -0.13
    stad
    -0.13
    anders
    -0.13
    ling
    -0.13
    POSITIVE LOGITS
    amac
    0.18
    fully
    0.16
     ÙħÙĤد
    0.14
    ena
    0.13
    antly
    0.13
    733
    0.13
    ASON
    0.13
     Ansi
    0.13
    ongyang
    0.13
    builtin
    0.13
    Activations Density 0.011%

    No Known Activations