INDEX

Explanations

expressions related to waiting or anticipation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

vard

-0.16

 Continued

-0.15

continued

-0.14

 berg

-0.14

 spent

-0.14

 ÐŁÑĢÐ¾Ð´

-0.14

 continued

-0.14

go

-0.13

 Public

-0.13

 Continuous

-0.13

POSITIVE LOGITS

 until

0.46

until

0.40

 Until

0.38

Until

0.37

 till

0.36

 hasta

0.31

 atÃ©

0.29

_until

0.29

 jusqu

0.27

 Till

0.26

Activations Density 0.044%

expressions related to waiting or anticipation

No Comments

No Known Activations