INDEX

Explanations

references to guiding concepts or moral guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð»ÐµÐ²

-0.17

ÐºÐ¾Ð´

-0.16

ahn

-0.15

íĶ¼

-0.14

essler

-0.14

ega

-0.14

ÐµÐ¹

-0.14

encion

-0.14

ulla

-0.13

 Ø³Ø§Ø²

-0.13

POSITIVE LOGITS

boro

0.17

stown

0.17

 principles

0.17

 Principles

0.15

 principle

0.15

.scalablytyped

0.15

 Principle

0.14

ismet

0.14

OperationException

0.14

oyal

0.14

Activations Density 0.015%

references to guiding concepts or moral guidelines

No Comments

No Known Activations