INDEX

Explanations

terms and references related to historical figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

usch

-0.15

gba

-0.15

avar

-0.15

moz

-0.14

ãĥ¼ãĤº

-0.14

 feas

-0.14

 fond

-0.14

 ÑĥÑĤ

-0.14

 Kons

-0.14

Ø±Ø¬

-0.13

POSITIVE LOGITS

Ã¸y

0.15

Äįel

0.14

mere

0.14

lyph

0.14

ateurs

0.14

cÃŃ

0.14

YPD

0.14

ìħĢ

0.14

.fig

0.13

ATTER

0.13

Activations Density 0.063%

terms and references related to historical figures and events

No Comments

No Known Activations