INDEX

Explanations

words indicating comparisons or evaluations of states, conditions, or entities

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

overe

-0.17

 Î£Ïħ

-0.16

)prepare

-0.15

ith

-0.15

utron

-0.15

ioni

-0.15

owell

-0.14

ornings

-0.14

jal

-0.14

 gord

-0.14

POSITIVE LOGITS

.GroupLayout

0.16

AAA

0.15

LAB

0.14

edia

0.14

 Sullivan

0.14

minus

0.14

CTR

0.14

ITED

0.14

Donate

0.14

entious

0.14

Activations Density 0.005%

words indicating comparisons or evaluations of states, conditions, or entities

No Comments

No Known Activations