INDEX

Explanations

phrases related to historical timelines and significant events

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

ad

-0.17

ovic

-0.16

exc

-0.15

 Flex

-0.14

igu

-0.14

ov

-0.14

oya

-0.13

Exc

-0.13

ÑıÐ½

-0.13

 Dawson

-0.13

POSITIVE LOGITS

ansi

0.17

ibold

0.16

izoph

0.15

.Next

0.15

ãĤ¸ãĤ¢

0.14

CRET

0.14

 insets

0.14

.addObject

0.14

yat

0.14

PEAT

0.14

Activations Density 0.008%

phrases related to historical timelines and significant events

No Comments

No Known Activations