INDEX

Explanations

key concepts related to differences, truths, challenges, and commonalities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 à¤Ĳà¤¸

-0.14

_DELETED

-0.14

/tos

-0.14

Č

-0.14

Ð·Ð½Ð°Ñĩ

-0.14

lya

-0.14

 ÑĤÐ°ÐºÐ¸Ð¼Ð¸

-0.14

maal

-0.14

 erotico

-0.13

UNUSED

-0.13

POSITIVE LOGITS

0.25

åı«

0.17

ÐµÐ½Ñĥ

0.17

taire

0.17

à¤¾:

0.14

riter

0.14

 called

0.14

 Reese

0.14

morgan

0.14

 Sawyer

0.14

Activations Density 0.129%

key concepts related to differences, truths, challenges, and commonalities in various contexts

No Comments

No Known Activations