INDEX

Explanations

references to discussions or negotiations

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

 Weekly

-0.16

-0.15

erken

-0.15

anio

-0.15

Tob

-0.15

 Bald

-0.15

bol

-0.14

 Imported

-0.14

 Confidence

-0.14

tob

-0.13

POSITIVE LOGITS

elines

0.15

ornings

0.15

wsp

0.14

ople

0.14

Ð¾ÑģÐ¿

0.14

Qin

0.14

nick

0.14

KHR

0.14

.instances

0.14

optera

0.14

Activations Density 0.003%

references to discussions or negotiations

No Comments

No Known Activations