INDEX

Explanations

repeated symbols or punctuation marks

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

stoff

-0.15

anax

-0.14

æľ«

-0.14

embr

-0.13

oreal

-0.13

onga

-0.13

arsi

-0.13

horn

-0.13

 eldre

-0.13

 Dans

-0.13

POSITIVE LOGITS

ayet

0.17

Tod

0.16

ÏħÎ¼

0.14

kla

0.14

 NAFTA

0.13

Äįen

0.13

ØµÙĩ

0.13

notation

0.13

cade

0.13

tml

0.13

Activations Density 0.129%

repeated symbols or punctuation marks

No Comments

No Known Activations