INDEX

Explanations

structured references to scientific journals and publications

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

 æ¸

-0.14

gorith

-0.14

tgt

-0.14

hari

-0.13

.RightToLeft

-0.13

uco

-0.13

Ã¶rt

-0.13

yer

-0.13

æ¯Ľ

-0.13

pts

-0.13

POSITIVE LOGITS

æŀ

0.15

 Merlin

0.14

Ple

0.14

.foundation

0.14

illon

0.14

usch

0.14

oka

0.13

elijk

0.13

 helicopt

0.13

tro

0.13

Activations Density 0.217%

structured references to scientific journals and publications

No Comments

No Known Activations