INDEX

Explanations

references to food and personal experiences related to dining

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 putas

-0.14

 Å¾Ã¡dnÃ½

-0.14

 Ð±ÑĥÐ´ÑĮ

-0.13

ampil

-0.13

ãģĵãģ¨ãģ«

-0.12

irm

-0.12

ampo

-0.12

 rÃ³wn

-0.12

enu

-0.12

.scalablytyped

-0.12

POSITIVE LOGITS

 years

0.52

 awhile

0.49

 recently

0.48

 ages

0.47

 last

0.44

 YEARS

0.44

 months

0.41

 yesterday

0.40

years

0.39

 previously

0.38

Activations Density 0.537%

references to food and personal experiences related to dining

No Comments

No Known Activations