INDEX

Explanations

references to unspecified or generic categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

itsu

-0.18

EqualTo

-0.18

ç²¾åĵģ

-0.16

empo

-0.15

 others

-0.15

avia

-0.14

others

-0.14

ViewById

-0.14

oints

-0.13

POSITIVE LOGITS

¶

0.16

ewise

0.16

oten

0.14

IFO

0.14

ost

0.14

/misc

0.13

podob

0.13

 Embassy

0.13

Ã¸r

0.13

Activations Density 0.027%

references to unspecified or generic categories

No Comments

No Known Activations