INDEX

Explanations

specifications related to document formatting and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ãĥ³ãĤ¬

-0.16

qe

-0.16

uthor

-0.16

labs

-0.15

lak

-0.15

esta

-0.15

/themes

-0.14

issen

-0.14

coni

-0.14

keit

-0.14

POSITIVE LOGITS

immel

0.16

Ã¦re

0.15

 Oasis

0.15

pressor

0.14

é¼ł

0.14

HH

0.14

unta

0.14

ovice

0.14

 confer

0.14

Spe

0.14

Activations Density 0.356%

specifications related to document formatting and structure

No Comments

No Known Activations