INDEX

Explanations

phrases related to connections and recommendations in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 thiáº¿u

-0.15

osy

-0.15

 authDomain

-0.14

rets

-0.14

/cop

-0.14

ActionCreators

-0.14

ãĤ¤ãĥ³ãĥĪ

-0.14

Ø¯Ø§Ø±

-0.13

oler

-0.13

.updateDynamic

-0.13

POSITIVE LOGITS

 release

0.39

 releasing

0.36

éĩĬ

0.36

 Release

0.36

 released

0.35

 destroy

0.34

 releases

0.34

 destruction

0.33

Release

0.33

 dispose

0.32

Activations Density 0.339%

phrases related to connections and recommendations in a context

No Comments

No Known Activations