INDEX

Explanations

references to various types of texts and their characteristics

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

est

-0.16

ÅĽ

-0.16

ab

-0.16

Ã«n

-0.16

dd

-0.15

ades

-0.15

ering

-0.14

.enter

-0.14

zn

-0.14

unter

-0.14

POSITIVE LOGITS

ilver

0.18

ured

0.17

ural

0.17

URED

0.17

ually

0.17

urally

0.15

URY

0.14

icular

0.14

urge

0.14

erior

0.14

Activations Density 0.017%

references to various types of texts and their characteristics

No Comments

No Known Activations