INDEX

Explanations

expressions of strong opinions or experiences related to services or personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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´me

-0.15

istol

-0.15

klad

-0.14

nop

-0.14

ecz

-0.14

igor

-0.14

åĤ

-0.14

UPS

-0.14

Act

-0.13

tring

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

/ajax

0.16

arn

0.15

 Observatory

0.14

tern

0.14

iam

0.14

arken

0.14

ern

0.13

ais

0.13

azer

0.13

Activations Density 0.004%

expressions of strong opinions or experiences related to services or personal experiences

No Comments

No Known Activations