INDEX

Explanations

phrases and concepts related to compatibility and fit within a team or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

vore

-0.16

ectl

-0.15

elligent

-0.15

ardash

-0.15

 Kenn

-0.14

 Kong

-0.14

ierarchical

-0.14

èŃ·

-0.14

ä¸įäºĨ

-0.14

enef

-0.14

POSITIVE LOGITS

etto

0.18

ys

0.17

allis

0.17

0.16

-fit

0.16

fit

0.15

-on

0.15

mesh

0.15

ynes

0.15

-valu

0.15

Activations Density 0.174%

phrases and concepts related to compatibility and fit within a team or organization

No Comments

No Known Activations