INDEX

Explanations

questions or interrogative phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

arters

-0.16

Ã

-0.16

ymes

-0.15

arter

-0.14

ÇĲ

-0.14

kees

-0.14

orage

-0.14

pcf

-0.14

_TestCase

-0.13

ught

-0.13

POSITIVE LOGITS

plat

0.16

-validator

0.15

cai

0.14

akat

0.14

 Unity

0.14

 åĸ

0.14

jo

0.14

kul

0.13

ITS

0.13

 analogy

0.13

Activations Density 0.026%

questions or interrogative phrases

No Comments

No Known Activations