© 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. 28-LLAMASCOPE-RES-32K
    11. 189
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FromDate
    -0.12
    TOT
    -0.11
    ìŀ¥ìĿĢ
    -0.11
    å¼Ħ
    -0.11
    lena
    -0.11
    ÑĤÑĥÑĢа
    -0.11
    озна
    -0.10
     ÙĦÙĩا
    -0.10
    ãģĿãĤĮãģ¯
    -0.10
    FromArray
    -0.10
    POSITIVE LOGITS
     to
    1.08
    	to
    0.56
    to
    0.56
     να
    0.54
     Äijá»ĥ
    0.52
     ÑĩÑĤобÑĭ
    0.52
    _to
    0.45
    ãĤĴ
    0.43
    sto
    0.42
     To
    0.41
    Activations Density 4.290%

    No Known Activations