INDEX

Explanations

references to the UK

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

OrUpdate

-0.18

mund

-0.15

ments

-0.15

axe

-0.14

aurus

-0.14

itu

-0.14

orgh

-0.14

 CircularProgress

-0.14

chia

-0.14

ÑīÐµ

-0.14

POSITIVE LOGITS

uran

0.19

-wide

0.18

ZN

0.17

/world

0.16

RAIN

0.16

ran

0.16

VI

0.16

cak

0.16

-American

0.15

rai

0.15

Activations Density 0.019%

references to the UK

No Comments

No Known Activations