INDEX

Explanations

keywords related to mythology and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Levin

-0.18

igator

-0.15

aro

-0.15

OVE

-0.15

DataStream

-0.14

ç¯Ģ

-0.14

ogn

-0.14

ãĥªãĥ³ãĤ°

-0.14

èĬĤ

-0.14

/Branch

-0.14

POSITIVE LOGITS

0.18

GST

0.15

ami

0.14

 tack

0.14

ister

0.14

utsche

0.14

ayar

0.14

aria

0.14

reur

0.13

nofollow

0.13

Activations Density 0.014%

keywords related to mythology and legal terminology

No Comments

No Known Activations