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. 18-LLAMASCOPE-RES-32K
    6. 25542
    Prev
    Next
    INDEX
    Explanations

    concepts related to data management and technological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dana
    -0.15
    YK
    -0.13
     tuy
    -0.13
    &_
    -0.13
    rido
    -0.13
     tavsiye
    -0.13
    eda
    -0.13
    quence
    -0.13
     |--------------------------------------------------------------------------↵
    -0.13
     ëķĮ문
    -0.13
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.29
    then
    0.26
     then
    0.25
     à¹ģล
    0.23
    ï¼ĮçĦ¶åIJİ
    0.23
     THEN
    0.21
     rá»ĵi
    0.19
    _then
    0.19
    å¹¶
    0.19
     alıp
    0.19
    Activations Density 0.477%

    No Known Activations