INDEX

Explanations

references to dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 commodity

-0.15

MT

-0.14

onal

-0.14

uble

-0.14

 pierced

-0.14

kr

-0.14

 pier

-0.13

Flat

-0.13

lena

-0.13

POSITIVE LOGITS

ardu

0.20

ReuseIdentifier

0.18

 returnUrl

0.16

arkan

0.16

ahun

0.16

Sep

0.16

iÅŁti

0.15

dale

0.14

ogany

0.14

iba

0.14

Activations Density 0.006%

references to dates and times

No Comments

No Known Activations