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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.xtext

-0.16

ê¸ī

-0.15

ilib

-0.15

TargetException

-0.14

ervo

-0.14

 konkrÃ©t

-0.14

RCT

-0.14

amment

-0.14

Ã¶t

-0.14

èŀ

-0.13

POSITIVE LOGITS

gy

0.17

THB

0.15

 Adults

0.15

erb

0.15

nic

0.14

att

0.14

 adults

0.13

 Norris

0.13

_<?

0.13

avin

0.13

Activations Density 0.119%

possessive forms of nouns

No Comments

No Known Activations