INDEX

Explanations

terms related to programming, code changes, and software development concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÏĮÏģ

-0.16

uraa

-0.15

ader

-0.15

.touch

-0.15

 Sanayi

-0.15

isan

-0.14

beit

-0.14

 TOUCH

-0.14

zan

-0.14

OLVE

-0.14

POSITIVE LOGITS

 permet

0.25

 allowing

0.24

 enabling

0.23

 allows

0.21

 enables

0.21

 allow

0.20

 enable

0.20

åħģ

0.19

allows

0.19

permit

0.19

Activations Density 0.026%

terms related to programming, code changes, and software development concepts

No Comments

No Known Activations