INDEX

Explanations

references to specific locations, buildings, and events

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

ilar

-0.15

akte

-0.15

.sourceforge

-0.15

adget

-0.15

-0.14

ÙĨÙħ

-0.14

èĻ«

-0.14

UTE

-0.14

ertext

-0.14

 Ð²Ð¸Ð´

-0.14

POSITIVE LOGITS

inden

0.17

combe

0.17

byn

0.16

 Parade

0.16

 Street

0.16

shall

0.16

 Court

0.15

 warmed

0.15

merce

0.14

hay

0.14

Activations Density 0.114%

references to specific locations, buildings, and events

No Comments

No Known Activations