INDEX

Explanations

elements related to user interface components and interactions within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ActivityIndicatorView

-0.20

ScrollIndicator

-0.20

illez

-0.16

ombine

-0.15

-widgets

-0.15

à¸Ĺà¸¢

-0.15

icense

-0.15

zcze

-0.15

adro

-0.15

à¸§à¸¢

-0.15

POSITIVE LOGITS

 click

0.50

 onClick

0.46

 Click

0.45

click

0.45

 clicked

0.44

_click

0.42

Click

0.41

 onclick

0.41

 clicking

0.40

 clicks

0.40

Activations Density 0.097%

elements related to user interface components and interactions within code

No Comments

No Known Activations