INDEX

Explanations

numeric values and financial terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

bsd

-0.14

NB

-0.14

LOBAL

-0.14

BEL

-0.14

.factor

-0.14

ANN

-0.14

ÅŁt

-0.13

isl

-0.13

Muj

-0.13

POSITIVE LOGITS

 thousands

0.18

ardy

0.18

chwitz

0.16

esity

0.15

agma

0.15

inel

0.15

OTES

0.14

 Ø§Ø·

0.14

urger

0.14

 hundreds

0.14

Activations Density 0.226%

numeric values and financial terms

No Comments

No Known Activations