INDEX

Explanations

references to the pronoun "it."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

entes

-0.16

roi

-0.15

anzeigen

-0.14

ripp

-0.14

ibo

-0.14

 ping

-0.14

 Tunnel

-0.14

tach

-0.14

essler

-0.13

 honey

-0.13

POSITIVE LOGITS

oger

0.15

mekte

0.14

nth

0.14

kee

0.14

Î»Î¹Î¿

0.14

osten

0.14

Ľi

0.14

0.13

è§

0.13

aktu

0.13

Activations Density 0.015%

references to the pronoun "it."

No Comments

No Known Activations