INDEX

Explanations

phrases indicating a process of inquiry or connection

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

ActionCreators

-0.17

 Shir

-0.14

sir

-0.14

rael

-0.14

á»įn

-0.14

vou

-0.14

antz

-0.14

pry

-0.14

lod

-0.13

POSITIVE LOGITS

alli

0.16

abilia

0.15

nze

0.15

Ã¼t

0.14

:CGRect

0.14

è³¢

0.14

oho

0.14

Ah

0.14

Mil

0.14

OUN

0.14

Activations Density 0.168%

phrases indicating a process of inquiry or connection

No Comments

No Known Activations