INDEX

Explanations

product-related terms and descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

_probe

-0.15

 Trick

-0.15

isto

-0.15

Probe

-0.14

iah

-0.14

probe

-0.14

ingroup

-0.14

auge

-0.14

æĶ

-0.14

 scouting

-0.14

POSITIVE LOGITS

 case

0.24

ãĤ±ãĥ¼ãĤ¹

0.23

 Cases

0.22

 cases

0.21

 Case

0.20

 phone

0.19

Case

0.19

Cases

0.18

èĨľ

0.18

ä¿ĿæĬ¤

0.18

Activations Density 0.009%

product-related terms and descriptions

No Comments

No Known Activations