INDEX

Explanations

references to specific days and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.15

wich

-0.15

mino

-0.14

åĭ¢

-0.14

 price

-0.14

bserv

-0.14

åĬ¿

-0.13

serrat

-0.13

 Moran

-0.13

NN

-0.13

POSITIVE LOGITS

otts

0.18

ioni

0.17

eded

0.15

asan

0.15

éĤ¦

0.14

Ð¿Ð¾ÑĢ

0.14

idden

0.14

unde

0.14

Activations Density 0.016%

references to specific days and times

No Comments

No Known Activations