INDEX

Explanations

instances of the word "begin" and its variations or related phrases indicating initiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

cil

-0.16

.scalablytyped

-0.15

adesh

-0.15

åħ¥åı£

-0.15

 Starting

-0.15

Starting

-0.14

aben

-0.14

æ¯

-0.14

uci

-0.14

bidden

-0.13

POSITIVE LOGITS

 begin

0.38

begin

0.34

.begin

0.31

 begins

0.30

 Begin

0.29

 began

0.28

Begin

0.27

	begin

0.25

 BEGIN

0.25

 begun

0.24

Activations Density 0.010%

instances of the word "begin" and its variations or related phrases indicating initiation

No Comments

No Known Activations