INDEX

Explanations

expressions related to commonalities and shared traits

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

arris

-0.17

yre

-0.17

æ°Ķ

-0.15

etta

-0.15

ibile

-0.15

etti

-0.15

-0.14

ÙħÙĬ

-0.14

oge

-0.14

yr

-0.14

POSITIVE LOGITS

 across

0.17

_Common

0.16

Across

0.16

 Across

0.16

 alike

0.15

_between

0.15

/Common

0.14

 Ä°z

0.14

subtract

0.14

Bounding

0.14

Activations Density 0.129%

expressions related to commonalities and shared traits

No Comments

No Known Activations