INDEX

Explanations

mathematical relationships and dependencies related to functions and variables

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ATTRIBUTE

-0.16

iona

-0.16

erdem

-0.15

ion

-0.15

ãĥĢãĤ¤

-0.15

oq

-0.14

ond

-0.14

.componentInstance

-0.14

Ã¦re

-0.14

egration

-0.14

POSITIVE LOGITS

 supply

0.17

avar

0.16

 factors

0.16

 Bookmark

0.15

 conf

0.15

 Hanson

0.15

Äįet

0.15

 Upper

0.15

hoe

0.14

cur

0.14

Activations Density 0.095%

mathematical relationships and dependencies related to functions and variables

No Comments

No Known Activations