INDEX

Explanations

phrases related to critical questioning and skepticism towards conventions and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ardin

-0.16

illin

-0.16

ubern

-0.15

??

-0.14

pps

-0.14

marvin

-0.14

ufig

-0.14

ìĬ¤íħĮ

-0.14

oro

-0.14

dic

-0.14

POSITIVE LOGITS

 à¤ĩà¤¤à¤¨

0.15

rint

0.15

Rem

0.15

ÐµÐºÑĤ

0.14

Ø§Ø¹ÙĬ

0.14

ahu

0.14

dsp

0.14

 ÏĦÏĮÏĥÎ¿

0.14

LOOR

0.13

noun

0.13

Activations Density 0.145%

phrases related to critical questioning and skepticism towards conventions and authority

No Comments

No Known Activations