INDEX

Explanations

references to figures and tables within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Burnett

-0.15

errMsg

-0.15

ui

-0.14

 Briggs

-0.14

 Dumpster

-0.13

edy

-0.13

hton

-0.13

erre

-0.13

ibt

-0.13

dac

-0.13

POSITIVE LOGITS

PageIndex

0.17

.scalablytyped

0.17

_KP

0.16

 Blasio

0.16

kle

0.15

duk

0.15

åºķ

0.15

 accordingly

0.14

AllowAnonymous

0.14

arella

0.14

Activations Density 0.063%

references to figures and tables within the text

No Comments

No Known Activations