INDEX

Explanations

phrases indicating a comprehensive service or solution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

uns

-0.14

gaard

-0.14

 subtype

-0.14

 chap

-0.14

 Loren

-0.14

rana

-0.14

uby

-0.14

enn

-0.14

 spor

-0.14

ÑĢÐ¾Ñĩ

-0.13

POSITIVE LOGITS

-stop

0.32

 stop

0.30

 source

0.29

 Stop

0.28

hub

0.27

 single

0.25

 resource

0.25

Stop

0.25

source

0.24

stop

0.24

Activations Density 0.125%

phrases indicating a comprehensive service or solution

No Comments

No Known Activations