INDEX

Explanations

elements related to code snippets and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑĭÑģ

-0.16

ighton

-0.15

alley

-0.15

 used

-0.15

Ø¨Ø·

-0.14

used

-0.14

.used

-0.14

.uml

-0.14

ORIZED

-0.13

ds

-0.13

POSITIVE LOGITS

 offer

0.54

 Offer

0.49

 offered

0.47

Offer

0.46

offer

0.45

 offering

0.43

 offers

0.43

 Offering

0.39

 ofrec

0.38

 ofere

0.37

Activations Density 0.148%

elements related to code snippets and programming concepts

No Comments

No Known Activations