INDEX

Explanations

programming-related keywords and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

canf

-0.16

ellen

-0.15

Rue

-0.14

robe

-0.14

far

-0.13

Ø±Ùĩ

-0.13

 Fork

-0.13

[~,

-0.13

æİĽ

-0.13

 approaches

-0.13

POSITIVE LOGITS

 verbose

0.17

 name

0.16

 force

0.16

 dtype

0.16

**

0.15

uset

0.15

ents

0.15

.scalablytyped

0.15

 mode

0.15

adows

0.15

Activations Density 0.035%

programming-related keywords and functions

No Comments

No Known Activations