INDEX

Explanations

interactions and relationships among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.15

uria

-0.15

ãĤ¾

-0.15

utch

-0.14

utin

-0.14

æ±Ĥ

-0.14

aim

-0.14

 Progressive

-0.14

abi

-0.14

_alarm

-0.13

POSITIVE LOGITS

 lesson

0.24

 later

0.21

lesson

0.18

later

0.17

 Lesson

0.17

Later

0.16

 lessons

0.16

rada

0.16

.lesson

0.15

 spÃ¤ter

0.15

Activations Density 0.287%

interactions and relationships among characters

No Comments

No Known Activations