INDEX

Explanations

references to geographic locations specifically in the eastern region

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

åłĤ

-0.16

raph

-0.15

eria

-0.14

 Claus

-0.14

erable

-0.14

çİĩ

-0.14

vip

-0.14

AndUpdate

-0.14

Ð¾Ð´Ð°

-0.13

 exquisite

-0.13

POSITIVE LOGITS

ward

0.21

most

0.17

ern

0.17

ablish

0.16

wards

0.16

BOUND

0.16

bound

0.15

WARD

0.15

 abund

0.15

sik

0.15

Activations Density 0.037%

references to geographic locations specifically in the eastern region

No Comments

No Known Activations