INDEX

Explanations

mentions of awards and recognitions

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

stoff

-0.16

gewater

-0.16

Ð»ÐµÐ¼

-0.15

opoly

-0.14

amen

-0.14

earch

-0.14

ooth

-0.14

ulet

-0.14

elman

-0.14

saldo

-0.14

POSITIVE LOGITS

 Truy

0.15

eron

0.14

erg

0.14

hung

0.14

acc

0.14

unction

0.14

ACC

0.14

ç¨

0.14

.Transactional

0.14

 hung

0.14

Activations Density 0.521%

mentions of awards and recognitions

No Comments

No Known Activations