INDEX

Explanations

references to technology and its implications in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģ¾ãģŁ

-0.19

 Ø£Ø®Ø±Ùī

-0.16

 instead

-0.16

 Ð´ÑĢÑĥÐ³Ð¾Ð³Ð¾

-0.15

ault

-0.15

onica

-0.15

 ãģĿãģ®ä»ĸ

-0.15

 another

-0.15

 other

-0.14

 Ð²Ð¼ÐµÑģÑĤ

-0.14

POSITIVE LOGITS

 whereas

0.23

çļĦæĺ¯

0.19

 Whereas

0.19

 obvious

0.17

 alone

0.16

Cad

0.15

 dabei

0.15

 simplement

0.15

 classic

0.15

 straightforward

0.15

Activations Density 0.315%

references to technology and its implications in various contexts

No Comments

No Known Activations