INDEX

Explanations

references to correspondence and communication in written form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

imler

-0.18

ForRow

-0.15

à¸µà¹ī

-0.15

ekli

-0.14

SizePolicy

-0.14

ethoven

-0.14

ëł¨

-0.14

enburg

-0.13

.makeText

-0.13

 wrought

-0.13

POSITIVE LOGITS

GLOSS

0.14

Hav

0.14

ILD

0.14

iferay

0.14

tron

0.14

Cad

0.13

-controls

0.13

 Mime

0.13

Cad

0.13

hang

0.13

Activations Density 0.041%

references to correspondence and communication in written form

No Comments

No Known Activations