INDEX

Explanations

references to assembly language syntax and operations related to registers 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

laÄį

-0.16

edback

-0.16

akens

-0.15

ãĥ¼ãĤº

-0.15

ifo

-0.15

erosis

-0.15

ichick

-0.15

anou

-0.14

raison

-0.14

ingham

-0.14

POSITIVE LOGITS

ELY

0.15

ml

0.15

.hibernate

0.14

 thÃ¢n

0.14

 Domino

0.14

 Indexed

0.13

wan

0.13

 indexed

0.13

ully

0.13

Activations Density 0.003%

references to assembly language syntax and operations related to registers and variables

No Comments

No Known Activations