© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 23368
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual related to watches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bic
    -0.14
     اÙĦسÙħ
    -0.13
    oli
    -0.13
    ismu
    -0.13
    æŀ¶
    -0.13
    byt
    -0.13
    atura
    -0.13
     apar
    -0.13
     poj
    -0.13
    acional
    -0.12
    POSITIVE LOGITS
    azes
    0.15
     wet
    0.14
    adÃŃ
    0.14
     Ders
    0.14
     aspir
    0.13
    .super
    0.13
    çģŃ
    0.13
    939
    0.13
    .tagName
    0.13
    ì°°
    0.13
    Activations Density 0.056%

    No Known Activations