INDEX

Explanations

phrases indicating commitments or agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

—↵↵

-0.15

 Ð»Ð¸Ð±Ð¾

-0.15

Ĭ¶

-0.14

/apt

-0.13

--)

-0.13

--)↵

-0.13

 ApiController

-0.13

--↵↵

-0.13

ãĢ

-0.13

.simps

-0.13

POSITIVE LOGITS

0.17

0.15

0.14

.:

0.14

 Heard

0.14

endi

0.13

0.12

Activations Density 0.604%

phrases indicating commitments or agreements

No Comments

No Known Activations

phrases indicating commitments or agreements

No Comments

No Known Activations