INDEX

Explanations

instructions related to organization and accessibility 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ookies

-0.15

ÑİÐº

-0.14

zzo

-0.14

iaux

-0.14

listen

-0.14

holm

-0.14

UFFIX

-0.13

unker

-0.13

ilogue

-0.13

clist

-0.13

POSITIVE LOGITS

 easily

0.35

 easy

0.35

 easier

0.31

 reference

0.30

 later

0.30

 Easily

0.29

 quickly

0.28

easy

0.27

 readily

0.27

 fÃ¡cil

0.26

Activations Density 0.201%

instructions related to organization and accessibility of information

No Comments

No Known Activations