INDEX

Explanations

names of historical or significant individuals and their relationships or associations

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

antic

-0.17

athi

-0.14

ati

-0.14

kova

-0.14

jab

-0.14

Ã©gor

-0.14

yc

-0.13

adow

-0.13

holm

-0.13

BAB

-0.13

POSITIVE LOGITS

ä»ĭ

0.16

èī

0.16

 clue

0.14

æµ©

0.14

èªĮ

0.14

-opacity

0.14

strcasecmp

0.13

_overflow

0.13

BOVE

0.13

Activations Density 0.246%

names of historical or significant individuals and their relationships or associations

No Comments

No Known Activations