INDEX

Explanations

terms related to war and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

estruction

-0.17

oo

-0.17

chen

-0.16

-chan

-0.15

eking

-0.15

elsing

-0.14

inction

-0.14

rossover

-0.14

Å¾ila

-0.14

ä¸»ç¾©

-0.13

POSITIVE LOGITS

lord

0.17

lords

0.15

zone

0.15

atile

0.15

AVA

0.15

ÑĢÐ°Ð¹

0.15

æľ«

0.14

minster

0.14

Zem

0.14

rier

0.14

Activations Density 0.039%

terms related to war and conflict

No Comments

No Known Activations