INDEX

Explanations

references to individuals and groups in educational or institutional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

IBE

-0.16

angling

-0.16

aling

-0.15

Launching

-0.15

elling

-0.14

Ã¶g

-0.14

 Selling

-0.14

compatible

-0.14

arÃŃa

-0.14

 RESPONS

-0.14

POSITIVE LOGITS

 being

0.63

being

0.48

 Being

0.40

 having

0.40

 sendo

0.38

Being

0.36

 becoming

0.36

 getting

0.32

è¢«

0.31

 siendo

0.31

Activations Density 0.265%

references to individuals and groups in educational or institutional contexts

No Comments

No Known Activations