INDEX

Explanations

punctuation marks and formatting in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

aylight

-0.17

uby

-0.15

antino

-0.14

Ã©ry

-0.13

riteln

-0.13

ãĢĤãģĬ

-0.13

Î³Î¬

-0.12

ekyll

-0.12

 Silva

-0.12

OfSize

-0.12

POSITIVE LOGITS

``

0.31

``

0.23

So

0.18

``↵

0.18

BT

0.17

 Cave

0.17

You

0.17

Æ¡

0.17

0.16

so

0.16

Activations Density 0.072%

punctuation marks and formatting in the text

No Comments

No Known Activations