INDEX

Explanations

mentions of significant numbers or important terms related to events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

abbo

-0.17

erdale

-0.15

ãĥªãĥ³ãĤ°

-0.15

aos

-0.14

ependency

-0.14

och

-0.14

RING

-0.14

ingly

-0.13

chg

-0.13

POSITIVE LOGITS

hood

0.15

¤íĶĦ

0.14

Latch

0.13

à¸¥à¸¥

0.13

emotion

0.13

Ø¢ÙĨ

0.13

ç¶

0.13

Ø§ÙĪÙĩ

0.13

 Hood

0.13

enville

0.13

Activations Density 0.096%

mentions of significant numbers or important terms related to events or figures

No Comments

No Known Activations