INDEX

Explanations

indicators and signals related to status or functionality of devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iba

-0.17

etur

-0.15

urator

-0.15

nem

-0.15

fully

-0.14

 Weiner

-0.14

 strat

-0.13

OfYear

-0.13

 prov

-0.13

 race

-0.13

POSITIVE LOGITS

 lights

0.15

dux

0.15

ãĥ³ãĤ¿

0.15

0.14

RowAt

0.14

jeta

0.14

usch

0.14

ÙĪØ§Ø±

0.14

ardu

0.14

Ã½n

0.14

Activations Density 0.035%

indicators and signals related to status or functionality of devices

No Comments

No Known Activations