INDEX

Explanations

aspects related to knowledge and awareness of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

âķĿ

-0.17

idot

-0.15

reon

-0.15

 :č↵

-0.15

è§

-0.15

onor

-0.15

.um

-0.14

ÐµÑİ

-0.14

urtles

-0.14

>NN

-0.14

POSITIVE LOGITS

 Forget

0.18

 forget

0.17

 impression

0.17

 anyone

0.16

yk

0.15

 persu

0.15

.bel

0.15

Forget

0.15

ugo

0.14

Activations Density 0.107%

aspects related to knowledge and awareness of information

No Comments

No Known Activations