INDEX

Explanations

prepositions and their related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

yle

-0.16

uros

-0.15

ÃĹ↵↵

-0.15

tober

-0.15

xies

-0.14

åľŁ

-0.14

 dagen

-0.14

peria

-0.14

velt

-0.13

hci

-0.13

POSITIVE LOGITS

olla

0.17

izz

0.16

æĢĿãģĦ

0.16

inati

0.15

azzo

0.14

 pÅĻÃŃleÅ¾it

0.14

voor

0.14

omination

0.14

.jd

0.14

lit

0.14

Activations Density 0.034%

prepositions and their related forms

No Comments

No Known Activations