INDEX

Explanations

references to organizations and partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

orra

-0.16

abay

-0.15

blr

-0.15

ÐºÐ¾ÑĤ

-0.15

.arm

-0.14

ARM

-0.14

ä¹

-0.14

dock

-0.14

erdale

-0.14

doch

-0.14

POSITIVE LOGITS

bourg

0.18

 nackte

0.15

esso

0.15

 ìĭ¸

0.14

.setRotation

0.14

/lic

0.14

 PRIV

0.14

vere

0.13

 dikke

0.13

nic

0.13

Activations Density 0.026%

references to organizations and partnerships

No Comments

No Known Activations