INDEX

Explanations

phrases conveying opinions or assessments of articles and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

owski

-0.14

oro

-0.14

 Glow

-0.14

resi

-0.13

conto

-0.13

unda

-0.13

ude

-0.13

 Tata

-0.13

 advantage

-0.13

lei

-0.13

POSITIVE LOGITS

/archive

0.15

ogui

0.14

ĶåĽŀ

0.14

/method

0.14

AMAGE

0.14

phant

0.14

ivement

0.14

 copp

0.14

abis

0.14

-regexp

0.13

Activations Density 0.075%

phrases conveying opinions or assessments of articles and discussions

No Comments

No Known Activations