INDEX

Explanations

punctuation marks, particularly those that indicate dialogue or emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

imbus

-0.15

-0.14

 erect

-0.14

uzzi

-0.14

 this

-0.14

mlin

-0.14

 outline

-0.14

↵

-0.13

POSITIVE LOGITS

_vue

0.18

 JsonRequest

0.15

.desktop

0.15

 piger

0.15

UsageId

0.15

 queryInterface

0.15

););↵

0.15

","");↵

0.14

rips

0.14

âĢ¦↵↵↵

0.14

Activations Density 0.167%

punctuation marks, particularly those that indicate dialogue or emotional expressions

No Comments

No Known Activations