INDEX

Explanations

elements and attributes from a markup or programming language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.addWidget

-0.15

.setWindowTitle

-0.14

éļĨ

-0.14

Ð±Ñĥ

-0.14

ussen

-0.14

velle

-0.14

issance

-0.13

uer

-0.13

 ELEMENT

-0.13

din

-0.13

POSITIVE LOGITS

 Fore

0.17

_fore

0.17

 Horizontal

0.17

.fore

0.16

 fore

0.16

ÙĥØª

0.16

 Background

0.15

 horizontal

0.15

SqlCommand

0.15

_enabled

0.15

Activations Density 0.020%

elements and attributes from a markup or programming language

No Comments

No Known Activations