INDEX

Explanations

references to stages and rankings in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.lv

-0.15

unde

-0.15

isle

-0.14

isce

-0.14

 Pron

-0.14

ole

-0.14

ews

-0.13

Ë

-0.13

ths

-0.13

POSITIVE LOGITS

ersh

0.16

Ã¶yle

0.15

Slinky

0.15

enek

0.15

usi

0.15

)prepare

0.15

 çī

0.15

DESC

0.15

)did

0.14

lyph

0.14

Activations Density 0.018%

references to stages and rankings in competitive contexts

No Comments

No Known Activations