INDEX

Explanations

phrases related to verification and oversight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

uj

-0.16

ger

-0.16

ÃŃnh

-0.15

bee

-0.15

Î¸Î»Î·

-0.15

osal

-0.14

insky

-0.14

ahun

-0.14

 Ã¡n

-0.14

POSITIVE LOGITS

/mit

0.19

zos

0.17

 Bulk

0.17

enie

0.16

opis

0.16

eneg

0.15

olon

0.14

 clickable

0.14

ETY

0.14

contre

0.14

Activations Density 0.226%

phrases related to verification and oversight

No Comments

No Known Activations