INDEX

Explanations

dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¤Ĺà¤²

-0.15

ÏĤ

-0.14

Ú¯ÙĦ

-0.14

erland

-0.14

lÃ¼

-0.13

ctrine

-0.13

hood

-0.13

iae

-0.13

wealth

-0.13

POSITIVE LOGITS

iko

0.14

 requisite

0.14

isol

0.13

åĦ¿

0.13

Ð½Ð°Ñĩ

0.13

zik

0.13

igli

0.13

utow

0.13

anager

0.13

iteur

0.13

Activations Density 0.051%

dates and times

No Comments

No Known Activations