INDEX

Explanations

references to historical context or 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

umd

-0.15

vig

-0.15

pn

-0.14

elm

-0.13

mw

-0.13

nout

-0.13

gid

-0.13

yll

-0.13

uy

-0.13

no

-0.13

POSITIVE LOGITS

 history

0.22

/history

0.19

-history

0.18

history

0.17

 History

0.17

ãĥĥãĤ·ãĥ¥

0.17

smarty

0.16

-addon

0.15

 Ð¸ÑģÑĤÐ¾ÑĢÐ¸Ð¸

0.15

à¹ģà¸ŀ

0.15

Activations Density 0.090%

references to historical context or events

No Comments

No Known Activations