INDEX

Explanations

references to accuracy and reporting related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

usz

-0.14

upiter

-0.14

polator

-0.14

serrat

-0.13

omanip

-0.13

teg

-0.12

 Ø¨Ø§Ø¯

-0.12

nat

-0.12

 Ð²ÐµÐ´ÑĮ

-0.12

CEEDED

-0.12

POSITIVE LOGITS

-NLS

0.14

\uD

0.13

UPDATED

0.13

ãĥ³ãĥ

0.13

skirts

0.13

Ã¼rnberg

0.13

carry

0.13

 blasph

0.12

 surviv

0.12

 Mavericks

0.12

Activations Density 26.313%

references to accuracy and reporting related to events

No Comments

No Known Activations