INDEX

Explanations

adverbs indicating uncertainty or probability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

polator

-0.17

VOKE

-0.14

 Gems

-0.14

Ð»Ð¸ÑĨ

-0.13

phans

-0.13

 sondern

-0.13

ãĢĤãĢĤ↵↵

-0.13

âĢļ

-0.13

uguay

-0.13

.mybatisplus

-0.13

POSITIVE LOGITS

ÏİÎ½ÏĦÎ±ÏĤ

0.17

ing

0.17

ajÄħc

0.17

 meaning

0.16

as

0.16

ÑĥÑİÑĩÐ¸

0.15

 because

0.15

cluding

0.15

 without

0.14

Activations Density 0.172%

adverbs indicating uncertainty or probability

No Comments

No Known Activations