INDEX

Explanations

references to awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.16

ops

-0.16

hu

-0.15

all

-0.15

 junk

-0.15

ekk

-0.15

 Garn

-0.14

å°ĸ

-0.14

 Eins

-0.14

aments

-0.14

POSITIVE LOGITS

 awards

0.18

 award

0.17

Award

0.17

 Award

0.17

.scalablytyped

0.16

è³ŀ

0.16

RAINT

0.16

 fund

0.15

FOUNDATION

0.15

 annually

0.15

Activations Density 0.076%

references to awards and recognitions

No Comments

No Known Activations