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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

urette

-0.18

arro

-0.17

anford

-0.16

rose

-0.15

bbe

-0.15

povÄĽ

-0.14

-ng

-0.14

\grid

-0.14

ÙĩÙĨ

-0.14

oÅĻ

-0.14

POSITIVE LOGITS

ople

0.17

0.15

 compos

0.15

to

0.15

umph

0.15

 brand

0.14

ium

0.14

ala

0.14

 distinct

0.14

som

0.14

Activations Density 0.047%

occurrences of the word "of"

No Comments

No Known Activations