INDEX

Explanations

mentions of specific products and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.lazy

-0.15

/util

-0.15

nest

-0.15

ReadStream

-0.14

lfw

-0.14

ÏĦÎ¹Î±

-0.13

chalk

-0.13

objs

-0.13

ĵĺ

-0.13

ÑģÐºÐ»Ð°Ð´

-0.13

POSITIVE LOGITS

Gam

0.17

osl

0.16

gam

0.16

Gam

0.16

gam

0.15

/english

0.15

 å¾

0.14

kah

0.14

olini

0.14

ÑĩÐ¸Ð¹

0.14

Activations Density 0.436%

mentions of specific products and their features

No Comments

No Known Activations