INDEX

Explanations

references to Hawaii and its islands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ottom

-0.16

§

-0.16

agit

-0.15

uset

-0.15

VD

-0.15

riad

-0.15

ynom

-0.15

.getOwnProperty

-0.15

uv

-0.15

Ø§Ø°

-0.14

POSITIVE LOGITS

 Islands

0.22

 Island

0.22

Alo

0.19

 Punch

0.19

 islands

0.19

 island

0.19

ensis

0.18

 Hawaiian

0.17

à¤¯à¤¨

0.17

Activations Density 0.006%

references to Hawaii and its islands

No Comments

No Known Activations