INDEX

Explanations

references to historical events and related timelines

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

iasi

-0.18

etxt

-0.15

aData

-0.15

 ÙħØ´Ø§Ø±

-0.14

ÅĻ

-0.14

von

-0.14

urma

-0.14

à¤¾à¤¯à¤²

-0.14

aines

-0.14

enza

-0.14

POSITIVE LOGITS

pop

0.21

Ã«

0.17

 President

0.16

ç

0.16

President

0.15

 monthly

0.15

 Month

0.15

 Monthly

0.15

 president

0.15

cro

0.15

Activations Density 0.020%

references to historical events and related timelines

No Comments

No Known Activations