INDEX

Explanations

occurrences of the preposition "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

itz

-0.17

rink

-0.17

-0.15

aukee

-0.15

 à¤¤à¤°

-0.15

zed

-0.15

/stretch

-0.14

alah

-0.14

ARP

-0.14

adows

-0.13

POSITIVE LOGITS

à¹ĥà¸Ī

0.17

ioni

0.15

rome

0.15

ple

0.15

interop

0.14

otel

0.14

Ã¼nd

0.14

Pinterest

0.14

ESP

0.14

ê¸Ī

0.14

Activations Density 0.059%

occurrences of the preposition "in."

No Comments

No Known Activations