INDEX

Explanations

phrases related to queries or requests to locate information or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

found

-0.16

FOUND

-0.15

urb

-0.15

iences

-0.15

eper

-0.14

à¸´à¸į

-0.14

kits

-0.14

alf

-0.14

Ã©ny

-0.14

.arm

-0.14

POSITIVE LOGITS

lay

0.28

ings

0.23

DOMNode

0.19

ley

0.19

NavController

0.19

INGS

0.18

lays

0.18

LAY

0.17

LEY

0.17

myp

0.17

Activations Density 0.020%

phrases related to queries or requests to locate information or items

No Comments

No Known Activations