INDEX

Explanations

terms related to formal processes and protocols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

weit

-0.17

-0.16

reen

-0.16

THON

-0.16

ê³Ħ

-0.15

indow

-0.15

bras

-0.15

ograd

-0.15

ÎµÎ²

-0.15

à¸ĩà¸²à¸Ļ

-0.14

POSITIVE LOGITS

urement

0.30

ional

0.27

EDURE

0.26

ess

0.20

inct

0.17

ual

0.17

.env

0.16

esse

0.16

ions

0.16

ural

0.16

Activations Density 0.032%

terms related to formal processes and protocols

No Comments

No Known Activations