INDEX

Explanations

references to specific people or entities and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.18

anik

-0.16

ÙĩØ±

-0.15

ritten

-0.15

 Lantern

-0.15

rama

-0.14

sis

-0.14

 effort

-0.14

ani

-0.13

 contr

-0.13

POSITIVE LOGITS

.removeListener

0.15

ToolTip

0.14

reature

0.14

ordum

0.14

æ²

0.14

ahr

0.14

åľĴ

0.14

enna

0.13

 èĭ

0.13

Activations Density 0.121%

references to specific people or entities and their relationships

No Comments

No Known Activations