INDEX

Explanations

references to historical events and numerical calculations related to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Gim

-0.16

.BorderFactory

-0.15

ìĭ¤

-0.14

ycz

-0.14

tement

-0.14

ure

-0.14

 Pointer

-0.14

roc

-0.14

ÏĩÎ¹

-0.13

Ìģ

-0.13

POSITIVE LOGITS

ampo

0.16

locker

0.15

inator

0.14

lige

0.14

axe

0.14

INTR

0.14

emer

0.13

itant

0.13

erral

0.13

dao

0.13

Activations Density 0.182%

references to historical events and numerical calculations related to time

No Comments

No Known Activations