INDEX

Explanations

questions and phrases about assistance and support

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

deen

-0.16

ãĥ³ãĥĩ

-0.16

rahim

-0.15

ovich

-0.15

recio

-0.15

shiv

-0.15

ugo

-0.14

åĶ±

-0.14

gons

-0.14

Ã¡le

-0.14

POSITIVE LOGITS

can

0.20

èĥ½å¤Ł

0.20

åı¯ä»¥

0.19

 could

0.18

èĥ½

0.17

 possibly

0.17

ability

0.16

ingham

0.16

Can

0.16

 Able

0.16

Activations Density 0.121%

questions and phrases about assistance and support

No Comments

No Known Activations