© 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. 30-LLAMASCOPE-RES-32K
    11. 23231
    Prev
    Next
    INDEX
    Explanations

    entities and key decision-making terms related to sports and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ìĭ±ê¸Ģ
    -0.16
    ziehung
    -0.15
    kün
    -0.15
    eldon
    -0.14
    룡
    -0.14
     Covered
    -0.14
     destin
    -0.14
    ToShow
    -0.13
    omik
    -0.13
    chrift
    -0.13
    POSITIVE LOGITS
     keeping
    0.26
    Keeping
    0.23
     sit
    0.22
    keeping
    0.21
     Keeping
    0.21
     within
    0.21
     keep
    0.20
    à¸łà¸²à¸¢à¹ĥà¸Ļ
    0.20
     inside
    0.20
    inside
    0.19
    Activations Density 0.042%

    No Known Activations