INDEX

Explanations

titles or ranks associated with characters, particularly those of authority or profession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

uco

-0.15

arius

-0.15

gers

-0.14

egin

-0.14

/MPL

-0.14

gv

-0.14

mani

-0.14

WISE

-0.13

genden

-0.13

ÎºÎµ

-0.13

POSITIVE LOGITS

ress

0.15

åºľ

0.14

thern

0.14

 Soph

0.14

ãģ¤ãģ¶

0.14

poj

0.14

 Zhao

0.13

ëŀį

0.13

 slic

0.13

eu

0.13

Activations Density 0.086%

titles or ranks associated with characters, particularly those of authority or profession

No Comments

No Known Activations