INDEX

Explanations

variations of the prefix "pre-" indicating preliminary or prior actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

fal

-0.16

flo

-0.16

abwe

-0.15

aze

-0.15

ref

-0.15

pected

-0.15

PropertyChanged

-0.15

sh

-0.15

rev

-0.14

xiety

-0.14

POSITIVE LOGITS

/post

0.25

ursors

0.23

/pre

0.22

 PREF

0.19

(pre

0.19

pre

0.18

iminary

0.18

empt

0.18

ursor

0.18

 Pref

0.18

Activations Density 0.029%

variations of the prefix "pre-" indicating preliminary or prior actions

No Comments

No Known Activations