INDEX

Explanations

terms related to technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÏĦÎ¿ÏĤ

-0.15

inho

-0.15

æķ£

-0.15

 Stitch

-0.15

å´İ

-0.15

isson

-0.14

çº¦

-0.14

OO

-0.14

erez

-0.14

íĮĲ

-0.14

POSITIVE LOGITS

ical

0.22

iques

0.22

ically

0.22

ologically

0.22

icolor

0.21

ological

0.21

icals

0.20

logy

0.20

ICAL

0.20

ologies

0.18

Activations Density 0.016%

terms related to technology

No Comments

No Known Activations