INDEX

Explanations

names of individuals and associated relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

#ab

-0.15

ekl

-0.14

 resultMap

-0.13

ÂŃn

-0.13

ISMATCH

-0.13

ÐĴÐ¡

-0.13

/WebAPI

-0.13

ydk

-0.13

kili

-0.13

.decorate

-0.13

POSITIVE LOGITS

odore

0.17

0.16

 Eugene

0.16

ÑħÐ¾Ð´

0.14

å«Į

0.14

ãĥ³ãĥĦ

0.14

.E

0.13

bum

0.13

£

0.13

Activations Density 0.168%

names of individuals and associated relationships

No Comments

No Known Activations