INDEX

Explanations

phrases indicating self-assurance and belief in one's abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-fashioned

-0.19

ward

-0.18

fen

-0.17

statt

-0.16

Ã¶n

-0.16

lings

-0.16

edException

-0.15

ÙĬØ¯ÙĬ

-0.15

atch

-0.15

æ´¥

-0.15

POSITIVE LOGITS

 intervals

0.18

ably

0.17

SSION

0.16

 interval

0.16

Ã©ment

0.16

ident

0.15

ancy

0.15

.nlm

0.15

 levels

0.15

 level

0.15

Activations Density 0.036%

phrases indicating self-assurance and belief in one's abilities

No Comments

No Known Activations