INDEX

Explanations

statements related to military operations and strategies

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

ennen

-0.16

bject

-0.15

.pretty

-0.14

iage

-0.14

loo

-0.14

 “[

-0.14

èĸ

-0.14

è¹

-0.14

peon

-0.14

chine

-0.13

POSITIVE LOGITS

 tomorrow

0.19

 ourselves

0.18

today

0.16

 incom

0.16

 today

0.16

 instruments

0.15

 President

0.15

plural

0.15

 Europe

0.15

 Naturally

0.14

Activations Density 0.108%

statements related to military operations and strategies

No Comments

No Known Activations