INDEX

Explanations

references to specific organizations or associations in a scientific or educational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð¸Ð´ÐµÐ½ÑĤ

-0.15

ea

-0.15

leme

-0.15

ince

-0.14

ugins

-0.14

erver

-0.14

 Source

-0.14

hower

-0.14

<typeof

-0.14

 ÑģÑĩ

-0.14

POSITIVE LOGITS

acci

0.16

ombre

0.15

 ragaz

0.15

ÙĦÙĤ

0.15

CHAIN

0.15

 Retrofit

0.14

 retrospect

0.14

readonly

0.14

|_|

0.14

arian

0.14

Activations Density 0.036%

references to specific organizations or associations in a scientific or educational context

No Comments

No Known Activations