© 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. 15-LLAMASCOPE-RES-32K
    11. 23633
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unf
    -0.15
    orman
    -0.14
    usz
    -0.14
    à¥ģह
    -0.14
     unpl
    -0.14
    ifornia
    -0.14
     PROF
    -0.13
    ë¹ĦìķĦ
    -0.13
    оÑĢи
    -0.13
     authentic
    -0.13
    POSITIVE LOGITS
     importance
    0.30
     significance
    0.29
     Importance
    0.25
    important
    0.21
    éĩįè¦ģ
    0.19
     Ñģимвол
    0.18
    สำà¸Ħ
    0.18
     importante
    0.18
     signific
    0.18
     Important
    0.18
    Activations Density 0.199%

    No Known Activations