INDEX

Explanations

occurrences of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kne

-0.15

apolis

-0.15

åł´

-0.14

irst

-0.14

ÑĮÐµ

-0.14

INU

-0.14

erge

-0.13

ode

-0.13

izations

-0.13

/releases

-0.13

POSITIVE LOGITS

atty

0.16

isan

0.16

AsStream

0.15

ndef

0.15

Ð¾Ð±Ð¾Ð²

0.15

ogan

0.14

ãĥ¼ãĤ¹

0.14

asket

0.14

\xff

0.14

kid

0.14

Activations Density 0.019%

occurrences of the word "of."

No Comments

No Known Activations