INDEX

Explanations

references to physical or metaphorical tables in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ipel

-0.18

ahn

-0.16

peror

-0.15

usher

-0.15

asto

-0.15

ToF

-0.15

lich

-0.15

indr

-0.15

adb

-0.14

POSITIVE LOGITS

PropertyValue

0.16

avors

0.15

rary

0.14

oit

0.14

issing

0.14

bers

0.14

 èĹ

0.14

 IsNot

0.14

 Peripheral

0.14

hel

0.13

Activations Density 0.018%

references to physical or metaphorical tables in various contexts

No Comments

No Known Activations