INDEX

Explanations

references to time periods and durations

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

acle

-0.16

Deal

-0.15

ata

-0.15

astro

-0.15

è¨ĢãģĦ

-0.14

asc

-0.14

 heaters

-0.14

atz

-0.14

outh

-0.13

ares

-0.13

POSITIVE LOGITS

Ä¢

0.14

ureau

0.14

usercontent

0.14

çĿ£

0.14

 Resets

0.13

raquo

0.13

[sizeof

0.13

AWN

0.13

çĨĬ

0.13

SourceType

0.13

Activations Density 0.459%

references to time periods and durations

No Comments

No Known Activations