INDEX

Explanations

keywords and alphanumeric codes related to product specifications and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 latter

-0.26

esa

-0.16

rike

-0.16

Ñĥ

-0.15

action

-0.15

-0.14

uard

-0.14

ueue

-0.14

ADE

-0.14

POSITIVE LOGITS

odore

0.21

/-

0.21

adays

0.18

#__

0.16

etheless

0.16

ï¸

0.16

riors

0.15

nbsp

0.15

ÛĮÙĨÙĩ

0.15

gether

0.15

Activations Density 0.152%

keywords and alphanumeric codes related to product specifications and measurements

No Comments

No Known Activations