INDEX

Explanations

references to events, appointments, and regulatory details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

izzo

-0.18

aida

-0.16

ingo

-0.15

achuset

-0.15

 ÑĤÐ°Ð±Ð»Ð¸

-0.15

querque

-0.15

 UCHAR

-0.14

 McCorm

-0.14

 Ð´Ð¾ÐºÑĥÐ¼

-0.14

ioneer

-0.14

POSITIVE LOGITS

GED

0.14

ENU

0.14

 LENG

0.14

iance

0.13

stry

0.13

ERVED

0.13

ume

0.13

AVED

0.13

.Tree

0.13

_exempt

0.12

Activations Density 4.654%

references to events, appointments, and regulatory details

No Comments

No Known Activations