INDEX

Explanations

references to the name 'Morgan' and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

icher

-0.17

ardon

-0.16

tÄĽ

-0.16

ural

-0.16

.timing

-0.16

AGR

-0.16

linger

-0.15

ider

-0.15

Ã³sito

-0.15

ê¹

-0.14

POSITIVE LOGITS

ìĦł

0.17

liness

0.16

UME

0.16

onian

0.15

nt

0.15

ization

0.15

ITES

0.15

shire

0.15

ian

0.14

rier

0.14

Activations Density 0.070%

references to the name 'Morgan' and its related forms

No Comments

No Known Activations