INDEX

Explanations

words related to user engagement and experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ooth

-0.17

-0.16

linkplain

-0.15

XH

-0.15

$$$$

-0.15

afort

-0.14

izik

-0.14

.selection

-0.14

igli

-0.14

usch

-0.14

POSITIVE LOGITS

 results

0.33

 outcome

0.31

 outcomes

0.29

ç»ĵæŀľ

0.28

 Results

0.27

results

0.26

 resultado

0.26

 Outcome

0.26

 RESULTS

0.26

 resultat

0.26

Activations Density 0.001%

words related to user engagement and experience

No Comments

No Known Activations

words related to user engagement and experience

No Comments

No Known Activations