INDEX

Explanations

symbols and annotations used in programming or code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

UA

-0.15

agini

-0.15

 masse

-0.14

Ð¾Ð²ÐµÑĢ

-0.14

Ain

-0.13

ih

-0.13

è£ľ

-0.13

 íĥĪ

-0.13

Jur

-0.13

Tie

-0.13

POSITIVE LOGITS

ereo

0.18

')."

0.15

slaught

0.15

-webpack

0.14

é¼ĵ

0.14

-gnu

0.14

/OR

0.14

.CustomButton

0.14

ona

0.14

.gmail

0.14

Activations Density 0.019%

symbols and annotations used in programming or code structure

No Comments

No Known Activations