INDEX

Explanations

discussions centered around moral ambiguity and differing opinions on right and wrong

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

ucu

-0.21

ëĿ¼ìĿ´

-0.16

orz

-0.15

 Westbrook

-0.14

iscard

-0.14

icari

-0.14

urahan

-0.14

 unless

-0.14

unless

-0.14

 flexible

-0.14

POSITIVE LOGITS

wake

0.15

ÐµÐ¶Ð°ÑĤÑĮ

0.15

æ²¿

0.15

amp

0.14

hardt

0.14

_iso

0.14

hle

0.14

gree

0.14

Ø§ÛĮØ±

0.14

deb

0.13

Activations Density 0.117%

discussions centered around moral ambiguity and differing opinions on right and wrong

No Comments

No Known Activations