INDEX

Explanations

numerical data and indicators related to performance or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

áº½

-0.17

emand

-0.14

enda

-0.14

otal

-0.14

errer

-0.14

acket

-0.14

ethod

-0.14

ota

-0.14

UGC

-0.14

geber

-0.14

POSITIVE LOGITS

0.16

istrovstvÃŃ

0.14

inke

0.14

illes

0.14

 Jess

0.14

rate

0.14

eka

0.14

_nested

0.13

gesch

0.13

 Rena

0.13

Activations Density 0.040%

numerical data and indicators related to performance or results

No Comments

No Known Activations