INDEX

Explanations

connections between ideas or arguments in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãĤ¤ãĥī

-0.16

ãĥ©ãĤ¤ãĥĪ

-0.15

çĶ±äºİ

-0.15

.AddListener

-0.14

bote

-0.14

¦

-0.14

ategories

-0.14

vÃ¡l

-0.14

urator

-0.14

ÑĢÑĥÐ±

-0.14

POSITIVE LOGITS

ora

0.16

å¹²

0.14

Ø®ÙĪØ§ÙĨ

0.14

 whence

0.13

ported

0.13

ently

0.13

olin

0.13

ivate

0.13

ORA

0.13

ÑĢÐ´

0.13

Activations Density 1.085%

connections between ideas or arguments in a discussion

No Comments

No Known Activations