INDEX

Explanations

terms related to imperfections or shortcomings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

«

-0.15

à¤¾à¤ĸ

-0.15

Ã¢ng

-0.15

 bloginfo

-0.14

kte

-0.14

layui

-0.14

utters

-0.14

ãģįãģŁ

-0.14

Ð³Ð¾ÑĢ

-0.14

Rpc

-0.13

POSITIVE LOGITS

0.15

fram

0.15

NL

0.14

tplib

0.14

acco

0.14

Ø¹Ø¯Ø§Ø¯

0.14

 Torch

0.14

NL

0.13

Internet

0.13

Activations Density 0.003%

terms related to imperfections or shortcomings

No Comments

No Known Activations