INDEX

Explanations

references to the existence of various issues, needs, or concerns in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lier

-0.16

elper

-0.15

itol

-0.15

orthand

-0.14

inkel

-0.14

Ð¿Ð¾Ñģ

-0.14

 rond

-0.14

ÙĨØ¯Ø§ÙĨ

-0.14

dÃ¡l

-0.13

vez

-0.13

POSITIVE LOGITS

 increasing

0.18

 tendency

0.17

 growing

0.17

kea

0.17

 Pins

0.16

 great

0.16

RIA

0.16

ipa

0.16

 strong

0.16

omba

0.15

Activations Density 0.094%

references to the existence of various issues, needs, or concerns in discussions

No Comments

No Known Activations