INDEX

Explanations

instances of interjections or expressions of emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ucer

-0.16

ucas

-0.15

olet

-0.15

 durumda

-0.15

\Configuration

-0.15

rosso

-0.15

Logging

-0.14

ÌĨ

-0.14

zel

-0.14

 Maiden

-0.14

POSITIVE LOGITS

 DCHECK

0.17

sic

0.14

Vul

0.14

rox

0.14

iva

0.14

 derec

0.14

0.13

igate

0.13

 Spicer

0.13

Activations Density 0.168%

instances of interjections or expressions of emphasis

No Comments

No Known Activations