INDEX

Explanations

references to time durations and years of service or involvement in various capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 soon

-0.25

 recently

-0.24

soon

-0.21

recent

-0.20

 quickly

-0.19

 recent

-0.18

 currently

-0.18

 eventually

-0.16

 lately

-0.16

æĪĲç«ĭ

-0.16

POSITIVE LOGITS

ç¶ļ

0.17

clus

0.15

hiba

0.14

ìĥģìĿĦ

0.14

ìĩ

0.14

 exclusively

0.14

 altern

0.14

avaÅŁ

0.14

tej

0.14

altern

0.14

Activations Density 0.109%

references to time durations and years of service or involvement in various capacities

No Comments

No Known Activations