INDEX

Explanations

references to parameters and their usage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

erman

-0.24

ermann

-0.18

strand

-0.16

arp

-0.15

ourn

-0.15

ening

-0.15

mans

-0.15

erties

-0.15

erm

-0.15

ern

-0.14

POSITIVE LOGITS

etrize

0.16

-Semit

0.15

ascus

0.15

Ð¾ÑĩÐ½Ð¾

0.15

ised

0.15

ized

0.15

 mÄ±

0.14

sthrough

0.14

.scalablytyped

0.14

ceased

0.14

Activations Density 0.041%

references to parameters and their usage in various contexts

No Comments

No Known Activations