INDEX

Explanations

sections of text that consist of various types of lines or formatting indicators, likely indicating structure or separation in code or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iras

-0.15

own

-0.15

isoft

-0.14

ansi

-0.14

 kino

-0.14

 bulletin

-0.13

ÚĺÙĩ

-0.13

lk

-0.13

 import

-0.13

.mk

-0.13

POSITIVE LOGITS

 MetroFramework

0.17

Î±Î½Î¬

0.14

 Garner

0.14

burn

0.14

eyh

0.14

 createState

0.14

ÑĭÐ¹

0.13

à¸¢à¸Ńà¸Ķ

0.13

avr

0.13

Inactive

0.13

Activations Density 0.013%

sections of text that consist of various types of lines or formatting indicators, likely indicating structure or separation in code or documents

No Comments

No Known Activations