INDEX

Explanations

references to competition outcomes and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aroo

-0.16

ÑĢÐµÑī

-0.15

Nur

-0.15

Orn

-0.14

otty

-0.14

goo

-0.14

ette

-0.14

ady

-0.14

bert

-0.14

POSITIVE LOGITS

/Peak

0.15

eken

0.15

á»ī

0.15

ï»¿#

0.14

zem

0.14

.IsAny

0.14

kra

0.14

ç¿°

0.14

isÃŃ

0.14

acid

0.13

Activations Density 0.042%

references to competition outcomes and awards

No Comments

No Known Activations