INDEX

Explanations

possessive 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Rivers

-0.17

eltas

-0.15

arges

-0.15

ksen

-0.15

Cash

-0.14

ped

-0.14

sta

-0.14

edik

-0.14

lement

-0.14

ilter

-0.13

POSITIVE LOGITS

OTES

0.16

utf

0.15

ultureInfo

0.15

IGO

0.15

ÑģÑĤÐ°Ð½Ð¾Ð²

0.15

riot

0.14

gency

0.14

urdy

0.14

duit

0.14

 Ãºn

0.14

Activations Density 0.103%

possessive forms of nouns

No Comments

No Known Activations