INDEX

Explanations

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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

arian

-0.15

trinsic

-0.15

ire

-0.14

\Context

-0.14

.Safe

-0.14

pk

-0.14

anal

-0.14

adil

-0.14

'gc

-0.14

ogn

-0.14

POSITIVE LOGITS

elen

0.17

erland

0.17

erdale

0.15

avia

0.15

ugal

0.15

áº±ng

0.15

tat

0.14

 Cheer

0.14

 Grant

0.14

Tat

0.14

Activations Density 0.069%

the preposition "in"

No Comments

No Known Activations