INDEX

Explanations

references to event participation and community involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ãºde

-0.16

ighbor

-0.15

_ctor

-0.14

Ã¨o

-0.14

ycled

-0.14

posables

-0.14

anax

-0.14

FormField

-0.13

 becoming

-0.13

ather

-0.13

POSITIVE LOGITS

 should

0.30

can

0.24

 please

0.23

should

0.21

Should

0.21

 Should

0.20

 must

0.20

may

0.20

 will

0.20

.should

0.19

Activations Density 0.084%

references to event participation and community involvement

No Comments

No Known Activations