INDEX

Explanations

references to promotional offers or discounts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iller

-0.18

antha

-0.17

 ëĭ¹

-0.15

awan

-0.15

anth

-0.15

pora

-0.15

ofi

-0.14

ovich

-0.14

 satisf

-0.14

unya

-0.14

POSITIVE LOGITS

ÑĢÑı

0.18

anc

0.18

ipl

0.15

 Reactive

0.15

Ana

0.15

.vaadin

0.14

ener

0.14

bur

0.14

xo

0.14

igid

0.14

Activations Density 0.009%

references to promotional offers or discounts

No Comments

No Known Activations