INDEX

Explanations

phrases indicating ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

uant

-0.16

 near

-0.16

idis

-0.14

ZH

-0.14

inde

-0.14

Me

-0.14

Near

-0.14

Î¼Î¬

-0.14

hol

-0.14

 Near

-0.14

POSITIVE LOGITS

 straight

0.31

 Straight

0.30

straight

0.28

Straight

0.25

 directly

0.22

 tháº³ng

0.20

 çĽ´

0.20

direct

0.20

 direct

0.19

çĽ´æİ¥

0.19

Activations Density 0.015%

phrases indicating ongoing actions or processes

No Comments

No Known Activations