INDEX

Explanations

programming-related syntax and identifiers, specifically focused on UI elements and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

odi

-0.18

oxy

-0.16

/archive

-0.15

igy

-0.15

unch

-0.15

ract

-0.15

rac

-0.14

 AppDelegate

-0.14

ignKey

-0.14

:↵

-0.14

POSITIVE LOGITS

lant

0.18

ingleton

0.17

ackers

0.16

ÅĻad

0.16

ÑıÑħ

0.15

å±Ģ

0.14

earer

0.14

à¤¹

0.14

ÏĢÎ·

0.14

berger

0.14

Activations Density 0.007%

programming-related syntax and identifiers, specifically focused on UI elements and attributes

No Comments

No Known Activations