INDEX

Explanations

references to intelligence or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istrovstvÃŃ

-0.21

 serialVersionUID

-0.18

gaard

-0.17

ëł

-0.16

orian

-0.16

ÑģÑı

-0.15

/Core

-0.15

ileo

-0.15

/by

-0.15

ork

-0.15

POSITIVE LOGITS

wine

0.19

0.18

gence

0.18

lectual

0.17

Brief

0.17

eum

0.17

ees

0.17

ently

0.16

IGENCE

0.16

 quot

0.15

Activations Density 0.015%

references to intelligence or related concepts

No Comments

No Known Activations