INDEX

Explanations

matching variations of the word "find" and phrases related to discovery or retrieval

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

 âĹĦ

-0.21

lify

-0.15

Dispatch

-0.15

ctest

-0.15

 Weather

-0.15

-0.14

è¿·

-0.14

Ã¼ml

-0.14

lain

-0.14

dling

-0.14

POSITIVE LOGITS

ings

0.33

able

0.30

INGS

0.23

ABLE

0.22

ables

0.21

ability

0.21

athon

0.20

ÂŃing

0.20

ers

0.19

Ing

0.17

Activations Density 0.227%

matching variations of the word "find" and phrases related to discovery or retrieval

No Comments

No Known Activations