INDEX

Explanations

references to office spaces and supplies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rap

-0.16

ÙĦØ§ØŃ

-0.16

è£ģ

-0.16

 nowhere

-0.16

NotificationCenter

-0.15

_cover

-0.15

kening

-0.15

ä¸įäºĨ

-0.14

 Chop

-0.14

over

-0.14

POSITIVE LOGITS

æ®Ĭ

0.15

hq

0.14

Ø³Ø·

0.14

ieg

0.14

 Truy

0.14

Gym

0.13

Ã¡ze

0.13

GPU

0.13

ETIME

0.13

klu

0.13

Activations Density 0.019%

references to office spaces and supplies

No Comments

No Known Activations