INDEX

Explanations

mentions of responses and evaluations related to products and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÙĪØ¬ÙĪØ¯

-0.15

.pan

-0.15

ä»¥ä¸Ĭ

-0.14

amic

-0.14

lotte

-0.14

imore

-0.14

inoa

-0.14

OFFSET

-0.14

ibaba

-0.13

vox

-0.13

POSITIVE LOGITS

is

0.22

 ÎµÎ¯Î½Î±Î¹

0.20

æĺ¯ä¸Ģ

0.17

 Ã¤r

0.17

are

0.15

Æ°á»Ŀng

0.15

etti

0.15

á»ĭ

0.14

JT

0.14

Activations Density 0.248%

mentions of responses and evaluations related to products and experiences

No Comments

No Known Activations