INDEX

Explanations

references to diverse groups of people or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

avanaugh

-0.17

gil

-0.14

asal

-0.14

olon

-0.14

ulaire

-0.14

å¢

-0.14

uring

-0.14

uche

-0.13

á»¡

-0.13

.rd

-0.13

POSITIVE LOGITS

 alike

0.20

olle

0.16

lej

0.15

rosso

0.15

pour

0.14

MouseListener

0.14

Jug

0.14

|/

0.14

alt

0.13

 Sunder

0.13

Activations Density 0.215%

references to diverse groups of people or organizations

No Comments

No Known Activations