© 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. 16-LLAMASCOPE-RES-32K
    11. 22389
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and water resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.22
    ãĥ£
    -0.21
    ãĥ¥
    -0.18
    ëĿ¼ëıĦ
    -0.16
    ãĤ§
    -0.15
    çı
    -0.14
    ÑĶ
    -0.14
     thá»ĥ
    -0.14
    amient
    -0.14
    ÑĶм
    -0.13
    POSITIVE LOGITS
    s
    1.55
    Ùĩ
    0.70
    ÏĤ
    0.63
    sik
    0.60
    ska
    0.60
    sburg
    0.59
    sand
    0.55
    sak
    0.55
    sian
    0.54
    sar
    0.53
    Activations Density 2.312%

    No Known Activations