INDEX

Explanations

references to situations or phenomena involving emotional or personal states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imd

-0.20

Ã¤tz

-0.17

ippet

-0.17

HING

-0.16

wig

-0.16

atetime

-0.16

herits

-0.14

ropdown

-0.14

kus

-0.14

mand

-0.14

POSITIVE LOGITS

 Whale

0.17

ais

0.15

seau

0.15

ÑıÑĤÐµÐ»ÑĮ

0.14

å£

0.14

abela

0.14

uzzi

0.13

ÑĩÐ°Ñģ

0.13

$body

0.13

ack

0.13

Activations Density 0.032%

references to situations or phenomena involving emotional or personal states

No Comments

No Known Activations