INDEX

Explanations

phrases indicating intentions or goals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

DM

-0.16

sb

-0.16

 Ø§ÙĦÙħØ¹

-0.16

ascus

-0.15

ÑĥÐ¹

-0.15

esar

-0.14

ihil

-0.14

RM

-0.14

ãģ¨ãģĦ

-0.14

erte

-0.13

POSITIVE LOGITS

.scalablytyped

0.15

onda

0.15

ÙĦÛĮÙħ

0.15

eted

0.13

à¹īà¸ĩ

0.13

 Anita

0.13

Ø¨Ø³

0.13

Injector

0.13

Ø¨ÙĪØ±

0.13

 Partner

0.13

Activations Density 0.068%

phrases indicating intentions or goals

No Comments

No Known Activations