INDEX

Explanations

questions expressing curiosity or disbelief about situations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

imo

-0.15

amat

-0.15

agar

-0.15

retty

-0.15

pd

-0.15

-0.14

Zus

-0.14

 DISCLAIM

-0.14

oret

-0.14

iro

-0.14

POSITIVE LOGITS

 possibly

0.22

 possible

0.18

possibly

0.17

 somehow

0.16

 justify

0.16

 posible

0.16

RCT

0.16

 managed

0.16

NECT

0.15

 possÃŃvel

0.15

Activations Density 0.081%

questions expressing curiosity or disbelief about situations or actions

No Comments

No Known Activations