INDEX

Explanations

phrases related to responsibilities and duties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÃĮ

-0.14

ï¼ĭ

-0.12

"..

-0.12

ï¼Ĩ

-0.12

Ã¢k

-0.11

é©¶

-0.11

ï½¥

-0.11

LineEdit

-0.11

 ï¼į

-0.11

ÐĴÑĤ

-0.11

POSITIVE LOGITS

 everything

0.14

 everywhere

0.14

íĸĪê³ł

0.13

orgh

0.12

 everyone

0.12

all

0.12

nard

0.12

Ã±ana

0.12

 even

0.12

xor

0.12

Activations Density 0.069%

phrases related to responsibilities and duties

No Comments

No Known Activations