INDEX

Explanations

relationships and connections among various elements and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

#elif

-0.16

ÙĬØ¯Ø§

-0.15

ocks

-0.15

esser

-0.15

TD

-0.14

 meisje

-0.14

 Ø¹ÙħØ±

-0.14

ÙĤØ¨

-0.14

_rgba

-0.14

è«¸

-0.14

POSITIVE LOGITS

 third

0.20

apore

0.18

 Third

0.17

ÐµÑĢÐ¶

0.16

ç¬¬ä¸ī

0.16

umble

0.16

bsite

0.15

third

0.15

 Lastly

0.15

Lastly

0.15

Activations Density 0.077%

relationships and connections among various elements and components

No Comments

No Known Activations