INDEX

Explanations

references to military operations and conflicts, particularly related to Iraq and Afghanistan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lage

-0.18

 Patron

-0.16

 protection

-0.15

 patron

-0.15

 teaching

-0.14

Dig

-0.14

imo

-0.14

Dig

-0.14

ams

-0.14

 Dude

-0.14

POSITIVE LOGITS

 Farrell

0.16

edback

0.15

Ot

0.15

.Abstractions

0.14

reib

0.14

à¤¾à¤¨à¤¨

0.14

alta

0.14

apes

0.14

ê·¼

0.14

è¿ĳ

0.14

Activations Density 0.023%

references to military operations and conflicts, particularly related to Iraq and Afghanistan

No Comments

No Known Activations