INDEX

Explanations

mentions of the city Tokyo

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

EMU

-0.15

Ñħ

-0.15

eson

-0.14

edly

-0.14

 Russ

-0.14

stood

-0.14

aves

-0.14

 Helena

-0.13

itu

-0.13

æīİ

-0.13

POSITIVE LOGITS

à¸¸à¸ĩ

0.15

inders

0.14

MBER

0.14

ilter

0.14

IPPING

0.14

stry

0.14

DAQ

0.14

/fs

0.13

olley

0.13

PM

0.13

Activations Density 0.010%

mentions of the city Tokyo

No Comments

No Known Activations