INDEX

Explanations

instances of significant change or transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Whenever

-0.23

 whenever

-0.22

 Whenever

-0.21

Upon

-0.20

 wherever

-0.20

 upon

-0.20

upon

-0.19

 WHILE

-0.18

_while

-0.18

 Upon

-0.18

POSITIVE LOGITS

wh

0.20

 happens

0.15

,$_

0.15

whe

0.15

Gul

0.15

ents

0.14

urs

0.14

Âł

0.14

uri

0.14

imi

0.14

Activations Density 0.083%

instances of significant change or transformation

No Comments

No Known Activations