INDEX

Explanations

brand names and specific product names related to technology and media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

heim

-0.17

adoo

-0.14

egment

-0.14

uin

-0.14

 Perry

-0.14

fl

-0.14

 Trem

-0.13

ìĺĪ

-0.13

æĿ

-0.13

pes

-0.13

POSITIVE LOGITS

ustil

0.17

avig

0.16

rav

0.16

orsche

0.15

jl

0.15

apro

0.14

iska

0.14

rys

0.14

 RectTransform

0.14

 Sesso

0.13

Activations Density 0.002%

brand names and specific product names related to technology and media

No Comments

No Known Activations