INDEX

Explanations

references to military ranks and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ocz

-0.19

idge

-0.16

opus

-0.15

atan

-0.15

jer

-0.15

thouse

-0.15

illis

-0.15

Deep

-0.14

uell

-0.14

POSITIVE LOGITS

 reserves

0.26

 reserve

0.26

 reserv

0.26

 Reserve

0.26

 activated

0.22

 activations

0.21

 activation

0.21

 drilling

0.20

activation

0.19

 Activation

0.19

Activations Density 0.051%

references to military ranks and structures

No Comments

No Known Activations