INDEX

Explanations

words and phrases related to technical specifications or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Î¼Î·

-0.18

ateria

-0.16

 Kurum

-0.15

oulos

-0.14

auc

-0.14

 èī

-0.14

iasi

-0.14

ught

-0.14

Margins

-0.14

uales

-0.14

POSITIVE LOGITS

 unlike

0.18

 generic

0.17

 extrem

0.15

bes

0.15

 onto

0.15

Ont

0.15

ile

0.14

 beyond

0.14

ushman

0.14

Activations Density 0.001%

words and phrases related to technical specifications or instructions

No Comments

No Known Activations