INDEX

Explanations

questions and statements that inquire about specifics or seek clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 anything

-0.16

erate

-0.15

-addon

-0.14

loff

-0.14

icios

-0.14

aphael

-0.14

acl

-0.13

Coder

-0.13

uffled

-0.13

ullet

-0.13

POSITIVE LOGITS

 else

0.24

soever

0.22

æł·çļĦ

0.21

ley

0.19

ToDo

0.18

leys

0.18

 happened

0.17

abouts

0.17

-ÑĤÐ¾

0.17

 happens

0.17

Activations Density 0.151%

questions and statements that inquire about specifics or seek clarification

No Comments

No Known Activations