INDEX

Explanations

negations in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

bum

-0.17

iasi

-0.17

oyer

-0.16

ookies

-0.14

 Wass

-0.14

aÅ¾

-0.14

ansom

-0.14

EGA

-0.14

idunt

-0.14

 elect

-0.13

POSITIVE LOGITS

inity

0.17

0.16

inos

0.15

spell

0.14

inf

0.14

 Beste

0.14

 Dodd

0.14

DIRECTORY

0.14

ãģ¤ãģ¶

0.14

Activations Density 0.049%

negations in sentences

No Comments

No Known Activations