INDEX

Explanations

phrases indicating decision-making and expressions of opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

aucoup

-0.18

oins

-0.18

 however

-0.16

ãģ®ãģ§

-0.16

á»©ng

-0.15

iÄħ

-0.15

so

-0.15

 Millet

-0.14

 Mund

-0.14

 jedoch

-0.14

POSITIVE LOGITS

 basically

0.22

 essentially

0.20

forth

0.17

 Basically

0.17

Basically

0.17

 accordingly

0.17

tl

0.16

jde

0.16

 yeah

0.16

 forth

0.15

Activations Density 0.193%

phrases indicating decision-making and expressions of opinion

No Comments

No Known Activations