INDEX

Explanations

elements related to formal communication or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥ«ãĥķ

-0.17

 wing

-0.17

-wing

-0.16

 wings

-0.15

ÙģØ§ÙĦ

-0.15

Ã½

-0.14

 stations

-0.14

 Pick

-0.14

 pick

-0.14

è¸

-0.13

POSITIVE LOGITS

.gpu

0.15

webtoken

0.15

esz

0.15

.dateFormat

0.15

ãĥ³ãĥĶ

0.15

ï¸

0.15

impan

0.15

ubble

0.14

ÑĪÐ¸Ð±

0.14

ispecies

0.14

Activations Density 0.008%

elements related to formal communication or documentation

No Comments

No Known Activations