INDEX

Explanations

conditional phrases indicating potential actions or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

sted

-0.16

asaki

-0.15

ingleton

-0.14

wich

-0.14

chez

-0.14

uling

-0.13

.scalablytyped

-0.13

ÅĽci

-0.13

wan

-0.13

BindingUtil

-0.13

POSITIVE LOGITS

've

0.39

nt

0.38

’ve

0.36

 conce

0.35

 easily

0.33

 well

0.32

 feas

0.29

 possibly

0.29

 potentially

0.29

/w

0.27

Activations Density 0.088%

conditional phrases indicating potential actions or outcomes

No Comments

No Known Activations

conditional phrases indicating potential actions or outcomes

No Comments

No Known Activations