INDEX

Explanations

specific terms indicating importance or features of items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 ãĢĮ

-0.16

uire

-0.16

cion

-0.16

Fol

-0.15

onia

-0.15

ropp

-0.15

.ide

-0.14

DAQ

-0.14

ãĢĤãĢĮ

-0.14

rud

-0.14

POSITIVE LOGITS

empre

0.15

 Äĳá»¡

0.15

[]

0.15

ãģªãģĮãĤī

0.15

Â»

0.14

ylum

0.14

/includes

0.14

å¤«äºº

0.14

()

0.13

Activations Density 0.281%

specific terms indicating importance or features of items or concepts

No Comments

No Known Activations