INDEX

Explanations

specific numerical data and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Kn

-0.15

uci

-0.15

argon

-0.15

ields

-0.14

andle

-0.14

Kn

-0.14

á»«ng

-0.14

åĦ¿

-0.14

 thÃ¡c

-0.14

acists

-0.13

POSITIVE LOGITS

cen

0.15

otton

0.15

íĭĢ

0.15

 Platt

0.15

nr

0.14

 ngang

0.14

 stabil

0.14

éĩĩ

0.14

 Overse

0.14

'gc

0.13

Activations Density 0.073%

specific numerical data and identifiers

No Comments

No Known Activations