INDEX

Explanations

phrases related to television episodes and their release

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-turned

-0.15

/by

-0.14

/--

-0.13

ched

-0.12

inger

-0.12

/j

-0.12

/as

-0.12

epad

-0.12

 rowData

-0.11

POSITIVE LOGITS

etc

0.21

etc

0.21

 ÑĤÐ¾ÑīÐ¾

0.20

 JAXBElement

0.16

 miscellaneous

0.15

 Miscellaneous

0.15

âĢ¦âĢ¦↵↵

0.14

Ø¶Ø§ÙĨ

0.14

 [âĢ¦

0.13

atd

0.13

Activations Density 1.420%

phrases related to television episodes and their release

No Comments

No Known Activations