INDEX

Explanations

code-related functions and operations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tica

-0.16

EMY

-0.15

iger

-0.14

<::

-0.14

iene

-0.14

 dÃŃ

-0.13

è²

-0.13

ĶåĽŀ

-0.13

 likewise

-0.13

POSITIVE LOGITS

ilib

0.17

ekl

0.16

undler

0.16

 simply

0.15

ansom

0.14

oldem

0.14

 Natural

0.14

mav

0.14

atural

0.14

adoo

0.14

Activations Density 0.024%

code-related functions and operations

No Comments

No Known Activations