INDEX

Explanations

adverbs that convey surprise or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ays

-0.15

åħĭæĸ¯

-0.14

åŀ

-0.14

lst

-0.14

 Leban

-0.14

 Hairst

-0.14

 Bernardino

-0.13

wsz

-0.13

å¾³

-0.13

 Monter

-0.13

POSITIVE LOGITS

forge

0.17

ÏĢÎ·

0.16

lijk

0.16

iae

0.16

GGLE

0.15

ÏĩÎµÎ´ÏĮÎ½

0.15

amble

0.15

 Holl

0.15

omal

0.15

ably

0.15

Activations Density 0.066%

adverbs that convey surprise or emphasis

No Comments

No Known Activations