INDEX

Explanations

titles of academic articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rack

-0.16

inges

-0.15

riteria

-0.15

ruk

-0.14

urvey

-0.14

Ø±Ø§Øª

-0.14

ang

-0.13

 Traff

-0.13

pag

-0.13

POSITIVE LOGITS

eless

0.18

afen

0.17

eft

0.14

abyrinth

0.14

lings

0.14

å¸Į

0.14

ë¶

0.14

dependent

0.14

åľŃ

0.14

 Wahl

0.14

Activations Density 0.007%

titles of academic articles

No Comments

No Known Activations