INDEX

Explanations

legal terms related to regulatory filings and registrants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

alled

-0.17

 Tate

-0.15

atz

-0.15

asio

-0.15

ITE

-0.14

elman

-0.14

aan

-0.14

eda

-0.14

ab

-0.14

ened

-0.14

POSITIVE LOGITS

heimer

0.17

ologne

0.15

/******/

0.14

repid

0.14

porn

0.14

ohon

0.14

<source

0.13

essler

0.13

shit

0.13

ARSE

0.13

Activations Density 0.035%

legal terms related to regulatory filings and registrants

No Comments

No Known Activations