INDEX

Explanations

references to pairs or groupings of individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ria

-0.17

Fav

-0.15

rians

-0.14

aktu

-0.14

rian

-0.14

zan

-0.14

idi

-0.14

idata

-0.14

owi

-0.13

hoe

-0.13

POSITIVE LOGITS

uxe

0.15

ifo

0.15

plet

0.14

Inflater

0.14

.cleanup

0.14

alu

0.14

Å¼e

0.14

erg

0.14

OTS

0.14

 aforementioned

0.13

Activations Density 0.048%

references to pairs or groupings of individuals or entities

No Comments

No Known Activations