INDEX

Explanations

references to written correspondence or letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

yon

-0.17

yah

-0.17

yun

-0.16

 collapsed

-0.16

sale

-0.16

yum

-0.16

àµįà´

-0.15

yt

-0.15

DDS

-0.14

ot

-0.14

POSITIVE LOGITS

abyrinth

0.18

PerPixel

0.17

press

0.17

 Letters

0.16

ìĹ´

0.16

 letters

0.16

-than

0.16

oden

0.16

xeb

0.15

lob

0.15

Activations Density 0.024%

references to written correspondence or letters

No Comments

No Known Activations