INDEX

Explanations

words related to the concept of "can" or ability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

thon

-0.17

 thÃ¡c

-0.16

ÏģÎ¹Î±

-0.15

baÅŁ

-0.15

itting

-0.15

ITY

-0.15

erti

-0.15

ry

-0.14

æĺŃ

-0.14

oles

-0.14

POSITIVE LOGITS

ing

0.19

woord

0.18

elope

0.18

elerik

0.16

ler

0.16

 Absolute

0.16

yaw

0.15

ucket

0.15

uario

0.15

Activations Density 0.034%

words related to the concept of "can" or ability

No Comments

No Known Activations