INDEX

Explanations

references to geographical directions, particularly focused on "north."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

aphael

-0.16

erate

-0.15

pany

-0.15

edla

-0.15

ãĥ¼ãĥĲ

-0.15

Åº

-0.15

ÑĪÐ¸Ð¼Ð¸

-0.14

etur

-0.14

peria

-0.14

AWN

-0.14

POSITIVE LOGITS

western

0.35

ward

0.30

-east

0.28

-west

0.26

bound

0.26

west

0.25

umberland

0.23

ampton

0.23

rup

0.22

wards

0.22

Activations Density 0.048%

references to geographical directions, particularly focused on "north."

No Comments

No Known Activations