INDEX

Explanations

negations and phrases suggesting a lack of agreement or compliance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anas

-0.16

ats

-0.16

ony

-0.15

izon

-0.15

allee

-0.14

ÙĪØ§Ø±

-0.14

Leh

-0.14

<tag

-0.14

TLS

-0.13

ascade

-0.13

POSITIVE LOGITS

 merely

0.19

.only

0.19

 mere

0.18

mere

0.17

 hanya

0.16

à¥ĩà¤µà¤²

0.16

åıªæĺ¯

0.15

Statics

0.15

ÑĢÐ¾Ð¿

0.14

 only

0.14

Activations Density 0.241%

negations and phrases suggesting a lack of agreement or compliance

No Comments

No Known Activations