INDEX

Explanations

references to academic or scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

–↵↵

-0.18

(--

-0.17

away

-0.17

(++

-0.16

urai

-0.15

 prob

-0.14

å¾Įãģ®

-0.14

-Con

-0.14

--+

-0.14

 ++↵

-0.14

POSITIVE LOGITS

0.41

 -↵

0.23

 -↵↵

0.20

_-_

0.19

 âĢĲ

0.18

-.

0.18

','-

0.17

-$

0.16

ernet

0.15

-(

0.15

Activations Density 0.024%

references to academic or scientific publications

No Comments

No Known Activations