INDEX

Explanations

references to technology and electronic devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 uniform

-0.15

 Subaru

-0.15

 Bosch

-0.15

elves

-0.14

 sadd

-0.14

gob

-0.14

Ã¤ch

-0.14

 overhead

-0.14

DOMNode

-0.13

 Wheels

-0.13

POSITIVE LOGITS

 Pocket

0.17

 rugged

0.17

Pocket

0.17

 pocket

0.17

 cáº§m

0.16

 sleek

0.15

è·Į

0.15

-pocket

0.15

_CELL

0.15

 compact

0.15

Activations Density 0.135%

references to technology and electronic devices

No Comments

No Known Activations