INDEX

Explanations

occurrences of punctuation or conjunctions that indicate lists or multiple items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÐºÑĥÑģ

-0.14

aben

-0.13

''↵

-0.13

åĲ¦

-0.12

 ê·¸ëĬĶ

-0.12

ãģ°ãģĭãĤĬ

-0.12

 cellForRowAt

-0.12

landÄ±rma

-0.12

gro

-0.12

 WHETHER

-0.12

POSITIVE LOGITS

 others

0.35

 among

0.34

etc

0.32

 amongst

0.31

etc

0.29

among

0.26

 numerous

0.25

 Others

0.25

 countless

0.24

 several

0.23

Activations Density 0.390%

occurrences of punctuation or conjunctions that indicate lists or multiple items

No Comments

No Known Activations