INDEX

Explanations

specific names or terms of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.resume

-0.14

 onResponse

-0.14

æºª

-0.14

olute

-0.14

lotte

-0.14

uteur

-0.13

zilla

-0.13

ÑįÑĤÐ¾Ð¼Ñĥ

-0.13

 derp

-0.13

/includes

-0.13

POSITIVE LOGITS

chia

0.15

 secondary

0.15

 Ã¢

0.15

Sch

0.14

 Rossi

0.14

 Secondary

0.14

 Rising

0.13

“

0.13

ç½®

0.13

Activations Density 0.233%

specific names or terms of people and places

No Comments

No Known Activations