INDEX

Explanations

constructs related to programming or coding, particularly within the context of data structures

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

erg

-0.16

emin

-0.16

.lu

-0.15

 Asset

-0.15

ÙĪØ§Ø±

-0.14

LTR

-0.14

Erg

-0.14

ods

-0.14

ÄħÅ¼

-0.14

 Myst

-0.14

POSITIVE LOGITS

 fresh

0.22

Fresh

0.21

 Fresh

0.21

rippling

0.21

 term

0.20

fresh

0.20

abox

0.19

 metavar

0.19

/terms

0.18

 binder

0.18

Activations Density 0.033%

constructs related to programming or coding, particularly within the context of data structures

No Comments

No Known Activations