INDEX

Explanations

terms related to technology and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

oreach

-0.16

wij

-0.15

 pylint

-0.14

ëĿ¼ëıĦ

-0.14

hra

-0.13

kel

-0.13

noch

-0.13

erable

-0.13

-selector

-0.13

ault

-0.13

POSITIVE LOGITS

 itself

0.17

 totiÅ¾

0.16

-ÑĤÐ¾

0.16

ãģ¨ãģ¯

0.15

ä¹ĥ

0.14

obus

0.14

 refers

0.14

 Cons

0.13

ollen

0.13

ãģĵãģĿ

0.13

Activations Density 0.167%

terms related to technology and programming concepts

No Comments

No Known Activations