INDEX

Explanations

references to problems or issues with various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

izzle

-0.18

 à¤ľà¤Ĺ

-0.17

iste

-0.16

 Rosenstein

-0.15

oky

-0.15

isko

-0.14

UFFIX

-0.14

asic

-0.14

ErrorException

-0.14

dy

-0.13

POSITIVE LOGITS

íħĶ

0.15

adle

0.15

amt

0.14

_pag

0.14

GLE

0.14

 bread

0.14

 dziew

0.14

 Å¡t

0.14

ãĥ¬ãĤ¹

0.14

zar

0.13

Activations Density 0.069%

references to problems or issues with various subjects

No Comments

No Known Activations