INDEX

Explanations

references to individuals or groups providing insider information or insights

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

 ÐŁÐ¾Ðº

-0.16

elyn

-0.15

haps

-0.15

ois

-0.14

leanup

-0.14

AZE

-0.14

.mob

-0.14

 Stocks

-0.14

stad

-0.13

à¸«

-0.13

POSITIVE LOGITS

.qq

0.18

 sources

0.17

 Anonymous

0.16

iero

0.16

 anonymously

0.15

å±ħ

0.15

 leaks

0.15

iges

0.15

abus

0.14

/sources

0.14

Activations Density 0.013%

references to individuals or groups providing insider information or insights

No Comments

No Known Activations