INDEX

Explanations

phrases indicating significant quantities or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 oneself

-0.14

 upon

-0.14

itzer

-0.14

¢

-0.14

çµ

-0.14

LOAT

-0.13

Upon

-0.13

 Upon

-0.13

edar

-0.13

æĸ

-0.13

POSITIVE LOGITS

Ped

0.16

chl

0.15

leta

0.15

pekt

0.14

ongan

0.14

hti

0.14

ipop

0.14

 Powers

0.14

PIO

0.14

Ã§ak

0.14

Activations Density 0.000%

phrases indicating significant quantities or comparisons

No Comments

No Known Activations