INDEX

Explanations

notices or announcements about important issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_LIBRARY

-0.15

stru

-0.14

com

-0.14

CONTEXT

-0.14

regor

-0.14

ault

-0.14

ÎºÎ®

-0.14

.portal

-0.13

 cÃ²n

-0.13

POSITIVE LOGITS

akash

0.15

 treff

0.14

dio

0.14

LOB

0.14

tiv

0.14

gang

0.14

edm

0.13

raki

0.13

.neo

0.13

geh

0.13

Activations Density 0.095%

notices or announcements about important issues

No Comments

No Known Activations