INDEX

Explanations

phrases related to legendary figures or stories

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

er

-0.23

eron

-0.19

alus

-0.18

age

-0.16

comb

-0.16

going

-0.15

rage

-0.15

ÑģÑı

-0.15

apas

-0.15

eres

-0.14

POSITIVE LOGITS

ARY

0.22

naire

0.22

Ã¤re

0.21

naires

0.21

ary

0.20

itimate

0.20

ario

0.19

airy

0.19

SHIP

0.18

imized

0.18

Activations Density 0.016%

phrases related to legendary figures or stories

No Comments

No Known Activations