INDEX

Explanations

concepts related to military operations and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

emento

-0.16

reece

-0.16

pector

-0.14

 Antar

-0.14

 padd

-0.14

 pardon

-0.14

ghi

-0.14

abled

-0.13

ousse

-0.13

esis

-0.13

POSITIVE LOGITS

imbus

0.18

osten

0.16

.flat

0.15

-fat

0.15

.pe

0.15

inch

0.15

strup

0.15

kum

0.14

dash

0.14

 withdrawal

0.14

Activations Density 0.033%

concepts related to military operations and conflicts

No Comments

No Known Activations