INDEX

Explanations

the plural forms of nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oftware

-0.19

itus

-0.17

ono

-0.16

-0.15

 Flint

-0.15

inus

-0.15

 Bret

-0.15

ebra

-0.14

gress

-0.14

own

-0.14

POSITIVE LOGITS

eki

0.14

ÙİØŃ

0.14

ubi

0.14

ala

0.14

APA

0.13

ersen

0.13

caff

0.13

_unref

0.13

ali

0.13

artial

0.13

Activations Density 0.089%

the plural forms of nouns

No Comments

No Known Activations