INDEX

Explanations

phrases indicating knowledge or understanding

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Module

-0.16

-modules

-0.15

angible

-0.15

.Module

-0.15

zik

-0.15

Module

-0.14

-module

-0.14

ModuleName

-0.14

éĥ

-0.14

POSITIVE LOGITS

eden

0.18

Ui

0.17

 admit

0.16

instr

0.15

ÑĥÐ¹

0.15

 Hayden

0.15

iale

0.15

çļ®

0.15

}->

0.15

ÃĹ↵↵

0.15

Activations Density 0.000%

phrases indicating knowledge or understanding

No Known Activations