INDEX

Explanations

terms related to financial metrics and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ulp

-0.16

akt

-0.15

 Kiss

-0.15

quia

-0.15

ym

-0.14

ials

-0.14

urch

-0.14

 reversible

-0.14

ulumi

-0.14

 Angel

-0.14

POSITIVE LOGITS

vik

0.17

 Gross

0.17

gross

0.15

ijn

0.15

gio

0.14

alars

0.14

avenport

0.14

iyas

0.14

rav

0.14

 Guid

0.14

Activations Density 0.012%

terms related to financial metrics and performance

No Comments

No Known Activations