INDEX

Explanations

technical terms related to software configuration and errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÙĪØªÛĮ

-0.17

azo

-0.15

osome

-0.14

istr

-0.14

 Mand

-0.14

oft

-0.14

èĬ

-0.14

 extended

-0.14

Mismatch

-0.14

POSITIVE LOGITS

ãĥĲãĤ¤

0.18

enet

0.16

Ã¦kke

0.14

alat

0.14

bservable

0.14

plode

0.14

edList

0.13

etta

0.13

olk

0.13

Ã¨le

0.13

Activations Density 0.171%

technical terms related to software configuration and errors

No Comments

No Known Activations