INDEX

Explanations

references to styles, roles, and contexts related to various subjects

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

zes

-0.21

zing

-0.16

asp

-0.15

esty

-0.14

aje

-0.14

 Morm

-0.14

hes

-0.13

rosso

-0.13

=num

-0.13

Gan

-0.13

POSITIVE LOGITS

whether

0.23

 whether

0.22

æĺ¯åĲ¦

0.22

 involved

0.18

Whether

0.18

.GroupLayout

0.18

zda

0.18

chosen

0.17

 Whether

0.17

æ¬¡

0.17

Activations Density 0.162%

references to styles, roles, and contexts related to various subjects

No Comments

No Known Activations