INDEX

Explanations

numerical ratings or scores associated with performances or reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

comm

-0.15

Ãºc

-0.14

etas

-0.14

ubl

-0.14

ÏĩÎ¿

-0.14

anium

-0.13

 Ãª

-0.13

æł¡

-0.13

IMER

-0.13

sat

-0.13

POSITIVE LOGITS

encil

0.16

 Ú©ÙĨ

0.15

insi

0.15

lou

0.14

esso

0.14

inyin

0.14

ITO

0.13

attachments

0.13

ãĤ¤ãĥī

0.13

Activations Density 0.000%

numerical ratings or scores associated with performances or reviews

No Comments

No Known Activations