INDEX

Explanations

terms related to arbitration and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

pread

-0.17

 oriented

-0.15

 parted

-0.14

ĮĢ

-0.14

åĲ¦

-0.14

mum

-0.14

ote

-0.14

 Slate

-0.14

 monot

-0.14

plain

-0.14

POSITIVE LOGITS

 TMPro

0.20

ttp

0.15

ssa

0.15

0.14

/blog

0.14

berman

0.14

 world

0.14

-ci

0.14

 ConsoleColor

0.14

.updateDynamic

0.14

Activations Density 0.011%

terms related to arbitration and legal proceedings

No Comments

No Known Activations