INDEX

Explanations

specific terms related to annotations and comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ignon

-0.17

 Ø§ÙĦØ§ØªØŃØ§Ø¯

-0.17

ALLED

-0.17

ont

-0.16

bet

-0.15

 major

-0.13

Syn

-0.13

AA

-0.13

.jp

-0.13

Î¯Î¶

-0.13

POSITIVE LOGITS

opp

0.15

Ø´ÙĬ

0.15

ymax

0.14

lÃ¼k

0.14

Î²Îµ

0.14

ÙĪØ³ÛĮ

0.14

_pb

0.14

fbe

0.13

olid

0.13

iyat

0.13

Activations Density 0.000%

specific terms related to annotations and comments

No Comments

No Known Activations