INDEX

Explanations

specific references to prior content, particularly focusing on transitions between sections or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ccoli

-0.17

irth

-0.16

isle

-0.15

DataExchange

-0.15

YNAM

-0.15

otland

-0.15

ToWorld

-0.15

ingu

-0.14

ovice

-0.14

POSITIVE LOGITS

-kit

0.15

pon

0.15

-stock

0.15

resents

0.14

 bottoms

0.14

illy

0.14

Ð°ÐºÐ¾Ð²

0.14

ool

0.14

 Koch

0.13

Activations Density 0.007%

specific references to prior content, particularly focusing on transitions between sections or topics

No Comments

No Known Activations