INDEX

Explanations

counts and references related to scientific data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Scha

-0.17

aler

-0.15

 regress

-0.14

umont

-0.14

reg

-0.14

usher

-0.14

wed

-0.13

cul

-0.13

POSITIVE LOGITS

(æ°´

0.17

ije

0.15

ijn

0.15

ogh

0.14

ead

0.14

;element

0.14

.om

0.14

à¸Ĭà¸£

0.14

Disposition

0.14

ETO

0.13

Activations Density 0.061%

counts and references related to scientific data and statistics

No Comments

No Known Activations