INDEX

Explanations

references to individuals' titles or credentials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-preview

-0.14

 Operand

-0.14

jours

-0.14

 opak

-0.13

 Merchant

-0.13

 Louisiana

-0.13

nton

-0.13

elez

-0.13

preload

-0.13

 ÎºÏģÎ±

-0.13

POSITIVE LOGITS

 losing

0.18

 individ

0.17

its

0.17

 lose

0.16

losing

0.16

 individual

0.16

indy

0.16

lost

0.16

 lost

0.15

 loses

0.15

Activations Density 0.029%

references to individuals' titles or credentials

No Comments

No Known Activations