INDEX

Explanations

phrases indicating uncertainty or opinion about a situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÑĤÐ¸Ðº

-0.18

 Benedict

-0.15

 firm

-0.14

bak

-0.14

æİªæĸ½

-0.14

 GOODS

-0.14

teil

-0.14

tip

-0.14

.persistence

-0.14

POSITIVE LOGITS

ÑĥÐ½Ð´

0.17

avec

0.15

ebin

0.15

_ASM

0.15

atel

0.14

 Horton

0.14

ariant

0.14

aint

0.14

aton

0.14

 vice

0.13

Activations Density 0.403%

phrases indicating uncertainty or opinion about a situation

No Comments

No Known Activations