INDEX

Explanations

references to software libraries and web development tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 granularity

-0.16

minent

-0.15

Fig

-0.14

lein

-0.14

 dict

-0.14

ijk

-0.14

ait

-0.14

 laid

-0.14

og

-0.14

POSITIVE LOGITS

.scalablytyped

0.21

.com

0.20

.gov

0.20

.edu

0.19

@nate

0.18

/downloads

0.17

.org

0.17

Ø§ÙĨÙĩ

0.15

thrown

0.15

iscard

0.15

Activations Density 0.021%

references to software libraries and web development tools

No Comments

No Known Activations