INDEX

Explanations

connections and relationships between different concepts or entities in the text

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

aphore

-0.15

ãģĵãĤĵãģ«

-0.14

arges

-0.13

lom

-0.13

 Trang

-0.13

 Kills

-0.13

isay

-0.12

ruits

-0.12

kills

-0.12

heet

-0.12

POSITIVE LOGITS

how

0.55

how

0.41

why

0.34

 cÃ³mo

0.31

 what

0.30

å¦Ĥä½ķ

0.30

 whether

0.28

 ways

0.28

its

0.26

-how

0.25

Activations Density 0.241%

connections and relationships between different concepts or entities in the text

No Comments

No Known Activations