INDEX

Explanations

the keyword "using" in various contexts, indicating its focus on coding or referencing modules and frameworks in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ovah

-0.15

igkeit

-0.15

 developmental

-0.15

forgettable

-0.14

itest

-0.14

ìĪĺ

-0.14

antt

-0.14

Ãłnh

-0.14

ald

-0.14

ÐłÐĺ

-0.13

POSITIVE LOGITS

dere

0.16

 Tato

0.16

 Dere

0.15

İ

0.14

Ø¹ÙĬ

0.14

Thi

0.14

 godt

0.13

 *);↵↵

0.13

arios

0.13

aru

0.13

Activations Density 0.026%

the keyword "using" in various contexts, indicating its focus on coding or referencing modules and frameworks in programming

No Comments

No Known Activations