INDEX

Explanations

mentions of significant events or actions related to military and geopolitical tensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã¢ng

-0.15

-slot

-0.15

uzey

-0.14

iddy

-0.14

undry

-0.14

 ëĭ¹ìĭľ

-0.14

 mastur

-0.14

 rencont

-0.14

 prefixed

-0.14

chwitz

-0.14

POSITIVE LOGITS

.rf

0.16

&#

0.15

 without

0.15

 Corona

0.15

 record

0.15

 Lamb

0.15

 towards

0.15

 VIDEO

0.15

 quar

0.14

Activations Density 0.079%

mentions of significant events or actions related to military and geopolitical tensions

No Comments

No Known Activations