INDEX

Explanations

names and titles associated with authority figures or officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

raya

-0.17

ÑģÑĮ

-0.16

zcze

-0.15

Î¿Îº

-0.15

ehr

-0.14

ÐµÐ½Ð·

-0.13

Ø§Ø¶Ø±

-0.13

ubi

-0.13

lix

-0.13

/tiny

-0.13

POSITIVE LOGITS

chet

0.19

olars

0.15

ÏĦÏİÎ½

0.15

gene

0.15

enticator

0.15

aversal

0.14

isk

0.14

 explanation

0.14

oproject

0.14

 explain

0.14

Activations Density 0.153%

names and titles associated with authority figures or officials

No Comments

No Known Activations