INDEX

Explanations

sections related to historical events and milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

pin

-0.16

olla

-0.15

lesia

-0.15

ela

-0.14

ibel

-0.14

eus

-0.14

 Ð§Ð¸

-0.13

è´¨

-0.13

URY

-0.13

 æŀ

-0.13

POSITIVE LOGITS

LD

0.16

erne

0.15

eway

0.15

Eld

0.15

edor

0.15

Ð¸ÑĤÐ¾Ð²

0.14

 ØªØ§Ø¨

0.14

assa

0.14

ecome

0.14

 Laden

0.14

Activations Density 0.092%

sections related to historical events and milestones

No Comments

No Known Activations