INDEX

Explanations

the word "of" and variations in its usage within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

umbo

-0.16

both

-0.15

ä¸Ģæ¬¡

-0.15

.djang

-0.15

’l

-0.15

 BOTH

-0.15

EXTERN

-0.14

 stuff

-0.14

/generated

-0.14

fang

-0.14

POSITIVE LOGITS

 several

0.21

 these

0.19

 them

0.16

 many

0.16

rippling

0.16

 those

0.15

abi

0.15

our

0.15

/all

0.15

 Several

0.14

Activations Density 0.083%

the word "of" and variations in its usage within a text

No Comments

No Known Activations