INDEX

Explanations

references to religious texts and teachings

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

Ã¡ng

-0.17

éº

-0.16

-0.15

ovice

-0.14

_ER

-0.14

Ø§ÙĤÙĦ

-0.14

ÑıÑħ

-0.14

immers

-0.14

hiba

-0.14

_NR

-0.13

POSITIVE LOGITS

ream

0.16

seg

0.15

mo

0.14

ac

0.14

jav

0.14

Ã¶z

0.14

 Dalton

0.13

jav

0.13

à¸£à¸ĵ

0.13

feld

0.13

Activations Density 0.163%

references to religious texts and teachings

No Comments

No Known Activations