INDEX

Explanations

references to technical issues and troubleshooting steps

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hee

-0.15

emand

-0.14

lue

-0.14

 WHATSOEVER

-0.14

Spacer

-0.14

Ã¥l

-0.14

("

-0.13

Hub

-0.13

ahi

-0.13

Uid

-0.13

POSITIVE LOGITS

yan

0.16

 Evrop

0.15

odd

0.15

erator

0.14

uka

0.14

ripp

0.14

stdlib

0.14

earned

0.14

ortal

0.14

.infinity

0.14

Activations Density 0.052%

references to technical issues and troubleshooting steps

No Comments

No Known Activations