© 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. 2-LLAMASCOPE-RES-32K
    11. 25367
    Prev
    Next
    INDEX
    Explanations

    programming and data structure terminology, particularly in the context of JSON and web development concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itag
    -0.17
    ëĭ¤ê°Ģ
    -0.15
     Evet
    -0.15
    bard
    -0.14
    .EventQueue
    -0.14
    immer
    -0.14
    Uploader
    -0.14
    .documentation
    -0.14
    Ùĩ
    -0.14
    ت
    -0.14
    POSITIVE LOGITS
    anz
    0.15
    rab
    0.14
    BT
    0.14
    abyrin
    0.14
    sch
    0.14
     forall
    0.14
    _nsec
    0.13
     Geh
    0.13
     Rough
    0.13
    ckett
    0.13
    Activations Density 0.275%

    No Known Activations