INDEX

Explanations

names of organizations or companies, especially in the context of investments and healthcare

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

ÐµÑģÐ°

-0.19

ÑĢÐ¾Ñĩ

-0.19

itti

-0.15

 ÂłÂł ÂłÂł ÂłÂł ÂłÂł

-0.15

steller

-0.14

ptrdiff

-0.14

ãĤ¤ãĤº

-0.14

itespace

-0.14

ÑģÐ°

-0.14

roj

-0.13

POSITIVE LOGITS

ANGER

0.15

ap

0.14

 fast

0.14

èĴĻ

0.14

 Netflix

0.13

fast

0.13

 embr

0.13

,www

0.13

org

0.13

Activations Density 0.059%

names of organizations or companies, especially in the context of investments and healthcare

No Comments

No Known Activations