INDEX

Explanations

words and concepts related to formal processes or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/dat

-0.15

yb

-0.15

UST

-0.15

ego

-0.15

ħn

-0.15

à¤Ĥà¤¶

-0.14

ÙĪ

-0.14

UME

-0.14

_STACK

-0.14

pot

-0.14

POSITIVE LOGITS

dehyde

0.23

/form

0.17

ities

0.17

aison

0.17

atted

0.16

 Formal

0.15

.eu

0.15

Ã¡i

0.15

antine

0.15

 formal

0.15

Activations Density 0.015%

words and concepts related to formal processes or structures

No Comments

No Known Activations