INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

utin

-0.16

*"

-0.14

ardo

-0.14

ÑĢÑĸÐ´

-0.14

aversal

-0.13

 ResourceType

-0.13

OOT

-0.13

 assoc

-0.13

hti

-0.13

avin

-0.13

POSITIVE LOGITS

idot

0.15

uÅ¡

0.14

fy

0.14

 Sesso

0.14

omanip

0.14

 splitted

0.13

 Ð½ÐµÑģÐ¿

0.13

outil

0.13

extent

0.13

Activations Density 0.792%

expressions of gratitude and appreciation

No Comments

No Known Activations

expressions of gratitude and appreciation

No Comments

No Known Activations