INDEX

Explanations

financial metrics and performance indicators related to earnings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rio

-0.14

ATTLE

-0.14

ãģ§ãģĻãģŃ

-0.14

.cum

-0.14

ouched

-0.13

erland

-0.13

 Mort

-0.13

ziej

-0.13

arrera

-0.13

ko

-0.13

POSITIVE LOGITS

 Wich

0.16

rightness

0.16

UEL

0.15

ãĥĶãĥ¼

0.14

à¸¥

0.14

ienia

0.14

ÙĦÙĦ

0.14

axon

0.14

ãĥ

0.14

Activations Density 0.016%

financial metrics and performance indicators related to earnings

No Comments

No Known Activations