INDEX

Explanations

phrases related to statistical analysis and measurement of effects in research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Jaune

-0.16

thur

-0.15

anca

-0.15

etas

-0.15

.Promise

-0.14

inue

-0.14

@mail

-0.14

ÙĪÛĮÙĩ

-0.14

ledi

-0.14

 Breitbart

-0.14

POSITIVE LOGITS

ynes

0.16

0.15

 grit

0.15

etten

0.15

elson

0.14

 households

0.14

Ø§Ø·

0.14

 Confirm

0.14

Wer

0.14

Activations Density 0.054%

phrases related to statistical analysis and measurement of effects in research findings

No Comments

No Known Activations