INDEX

Explanations

instances of the word "the" and variations of "the" in different contexts

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

-0.14

bsp

-0.14

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.14

won

-0.13

Toolkit

-0.13

åĴ¨

-0.13

ea

-0.13

_NS

-0.13

 Jens

-0.13

IENT

-0.13

POSITIVE LOGITS

orem

0.20

isman

0.18

odos

0.16

osen

0.16

,result

0.15

 resultant

0.15

RuleContext

0.15

YYS

0.15

.son

0.15

oretical

0.15

Activations Density 0.197%

instances of the word "the" and variations of "the" in different contexts

No Comments

No Known Activations