INDEX

Explanations

conjunctions and phrases indicating connections or relationships among ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

lein

-0.15

-0.14

icari

-0.14

zÃ¡

-0.14

edla

-0.14

aille

-0.14

aar

-0.13

andan

-0.13

th

-0.13

arence

-0.13

POSITIVE LOGITS

/or

0.24

rew

0.22

 zwar

0.21

Ð¾Ð²Ð¸

0.19

REW

0.17

hra

0.15

rea

0.15

rosso

0.15

rov

0.15

ei

0.15

Activations Density 0.156%

conjunctions and phrases indicating connections or relationships among ideas

No Comments

No Known Activations

conjunctions and phrases indicating connections or relationships among ideas

No Comments

No Known Activations