INDEX

Explanations

proper nouns and references to specific places or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Specifier

-0.17

Nos

-0.16

ë§¹

-0.16

meteor

-0.15

nar

-0.14

 ì¶ķ

-0.14

ãĥ³ãĥĶ

-0.14

ogan

-0.14

OutOfRangeException

-0.14

POSITIVE LOGITS

 Boss

0.18

 Tyler

0.18

0.17

 kÃ¼r

0.17

Ou

0.16

ossier

0.16

 cous

0.15

 sabah

0.15

 Negative

0.15

Activations Density 0.012%

proper nouns and references to specific places or organizations

No Comments

No Known Activations