INDEX

Explanations

conversational phrases asking about well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

nos

-0.18

aben

-0.16

ify

-0.15

 Relief

-0.15

nos

-0.15

VERR

-0.14

Veter

-0.14

nete

-0.14

_blk

-0.13

 ARISING

-0.13

POSITIVE LOGITS

 healthy

0.24

healthy

0.20

ä¸ĢåĪĩ

0.20

 enjoying

0.19

 khá»ıe

0.19

 health

0.18

urdy

0.18

 HEALTH

0.18

 Healthy

0.18

åģ¥åº·

0.18

Activations Density 0.195%

conversational phrases asking about well-being

No Comments

No Known Activations