INDEX

Explanations

references to watching videos and multimedia content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

osy

-0.16

AFX

-0.16

erving

-0.15

Ð¾Ð·Ð°

-0.14

à¸´à¸ªà¸ķ

-0.14

ingham

-0.14

mÃ¡

-0.14

AXB

-0.14

unt

-0.14

 Cheer

-0.14

POSITIVE LOGITS

plib

0.14

 tutorials

0.14

³

0.14

sumer

0.14

ByteArray

0.14

raman

0.14

ìĥģìľĦ

0.13

outube

0.13

rlen

0.13

angelog

0.13

Activations Density 0.089%

references to watching videos and multimedia content

No Comments

No Known Activations