INDEX

Explanations

various forms of words that suggest actions or states, especially those related to emotional or verbal expressions

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

Î»Î¿ÏĤ

-0.15

eder

-0.14

 Nack

-0.14

ookie

-0.14

issing

-0.14

leÅŁ

-0.14

icol

-0.13

aya

-0.13

ensis

-0.13

Ð¼ÐµÑĤÑĮ

-0.13

POSITIVE LOGITS

.bunifuFlatButton

0.15

bcm

0.13

arness

0.13

ubi

0.13

$MESS

0.13

SourceType

0.13

IVO

0.13

 ØªÙĥÙĬÙĬÙģ

0.13

(jQuery

0.12

ÐĲÑĢÑħÑĸÐ²

0.12

Activations Density 0.282%

various forms of words that suggest actions or states, especially those related to emotional or verbal expressions

No Comments

No Known Activations