INDEX

Explanations

expressions related to communication and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

akit

-0.16

inke

-0.15

LECT

-0.14

oved

-0.13

ãĥ³ãĥĩ

-0.13

 adulti

-0.13

otal

-0.13

ÏĨÎ¿

-0.13

itele

-0.13

abant

-0.13

POSITIVE LOGITS

 real

0.39

 very

0.36

 Real

0.35

 soon

0.34

SO

0.33

 shortly

0.30

 pretty

0.29

 REAL

0.29

 VERY

0.29

 Soon

0.29

Activations Density 0.112%

expressions related to communication and updates

No Comments

No Known Activations