INDEX

Explanations

references to press conferences and media briefings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ancer

-0.16

.party

-0.16

inki

-0.15

 Feedback

-0.15

åħ±åĴĮ

-0.15

Ð¸Ð¼Ð¾ÑģÑĤÑĮ

-0.14

ffer

-0.14

æ¢°

-0.14

ollo

-0.14

atab

-0.14

POSITIVE LOGITS

ãĥ¼ãĥĭ

0.17

Ľ

0.15

_scaling

0.15

 rtrim

0.15

iform

0.14

 press

0.14

isure

0.14

 injury

0.14

quate

0.14

 Injury

0.14

Activations Density 0.015%

references to press conferences and media briefings

No Comments

No Known Activations